Activity
From 09/09/2015 to 10/08/2015
10/08/2015
- 10:15 PM Feature #13419 (New): On osd startup we should log all configuration settings
For diagnosis of Ceph issues, it would be nice if looking a log you could see what the configuration settings were ...- 10:06 PM CephFS Bug #13334 (Resolved): delayed revoke warning in test_client_recovery test
- https://github.com/ceph/ceph/pull/6170
- 09:42 PM CephFS Bug #13364: LibCephFS locking tests are failing and/or lockdep asserting
- If somebody else wants to investigate this, feel free, but otherwise I'll try and get to it.
- 09:42 PM CephFS Bug #13364: LibCephFS locking tests are failing and/or lockdep asserting
- Sage says this passes when run against a vstart cluster.
- 04:22 AM CephFS Bug #13364: LibCephFS locking tests are failing and/or lockdep asserting
- https://github.com/ceph/ceph/pull/6200
fixes the path check.
These still fail:
[ RUN ] LibCephFS.InterP... - 08:55 PM Feature #12406: Support for building on Alpine Linux
- We've taken lots of changes to support building on alternative distributions and OSes. Smaller changes that can be ev...
- 08:26 PM Feature #12406: Support for building on Alpine Linux
- Been messing around with this.
https://github.com/dx9/build-alpine-ceph
https://github.com/dx9/ceph
It's a wor... - 08:45 PM devops Bug #13355 (Resolved): docker-test.sh fails because user root already exists
- 07:44 PM devops Bug #13355: docker-test.sh fails because user root already exists
- Right. There also is docker-test.sh --help though
- 07:41 PM devops Bug #13355: docker-test.sh fails because user root already exists
- OK, that works. Since that blog post appears to be the only documentation on ...
- 02:51 PM devops Bug #13355: docker-test.sh fails because user root already exists
- ...
- 02:22 PM devops Bug #13355: docker-test.sh fails because user root already exists
- I tried it again using your wip branch. I run the following commands:...
- 08:44 PM Revision 1e8cb9bc (ceph): Merge pull request #6173 from dachary/wip-13355-docker-test
- tests: allow docker-test.sh to run under root
Reviewed-by: Nathan Cutler <ncutler@suse.cz> - 08:37 PM Bug #13418 (Duplicate): some "s3tests.functional.test_*" failed in smoke-master-distro-basic-mult...
- #13240
- 08:29 PM Bug #13418 (Duplicate): some "s3tests.functional.test_*" failed in smoke-master-distro-basic-mult...
- Run: http://pulpito.ceph.com/teuthology-2015-10-08_05:00:08-smoke-master-distro-basic-multi/
Job: 1095235
Logs: htt... - 08:25 PM devops Backport #13417 (In Progress): Fix -Wno-format and -Werror=format-security options clash
- 08:23 PM devops Backport #13417: Fix -Wno-format and -Werror=format-security options clash
- The next thing that is breaking ...
- 08:22 PM devops Backport #13417 (Resolved): Fix -Wno-format and -Werror=format-security options clash
- https://github.com/ceph/ceph/pull/6207
- 08:24 PM Revision 7a8b6fb4 (ceph): Fix -Wno-format and -Werror=format-security options clash
- This causes build failure in latest fedora builds, ceph_test_librbd_fsx adds -Wno-format cflag but the default AM_CFL...
- 08:20 PM Revision 61d24d9d (ceph): Merge pull request #6194 from dillaman/wip-13220-infernalis
- rbd-replay-prep and rbd-replay improvements
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:23 PM Revision 1a2689f8 (ceph): ReplicatedPG::maybe_handle_cache: do not promote before checking full
- Otherwise, ops with need_promote() can order past ops without it
causing an rgw write sequence like:
writefull 0~0
w... - 06:03 PM rbd Feature #13274: LTTng-UST should be optionally enabled
- PR for master: https://github.com/ceph/ceph/pull/6135
- 05:44 PM Revision e8d375f8 (ceph): Merge pull request #6206 from rzarzynski/wip-rgw-manifest-skip
- rgw: add support for getting Swift's DLO without manifest handling
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 05:30 PM rbd Bug #13405 (Fix Under Review): rbd-replay-prep trace output is not version controlled
- *infernalis PR*: https://github.com/ceph/ceph/pull/6194
- 05:28 PM Revision e0d8cb12 (ceph): tests: removed obsolete rbd_replay test cases
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 05:27 PM Revision c2a83d0b (ceph): ceph-dencoder: new rbd_replay trace file types
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 05:21 PM Revision 3ecdae83 (ceph): rbd-replay: added version control to trace output file
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 05:10 PM Bug #13415 (Resolved): 11429.yaml failing due to writes going to wrong pool
- 04:48 PM Bug #7995: osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- http://pulpito.ceph.com/samuelj-2015-10-07_21:23:25-rados-wip-sam-testing-distro-basic-multi/1095098/
- 04:38 PM rbd Bug #13304: "TestLibRBD.Metadata , TestLibRBD.UpdateFeatures" tests failed in upgrade:client-upgr...
- Same in
Run: http://pulpito.ceph.com/teuthology-2015-10-04_23:20:02-upgrade:client-upgrade-infernalis-distro-basic-m... - 04:18 PM Revision 629b6314 (ceph): Merge pull request #5885 from Abhishekvrshny/wip-13034-hammer
- osd: copy-from doesn't preserve truncate_{seq,size}
Reviewed-by: Sage Weil <sage@redhat.com> - 04:10 PM devops Bug #12382: Package python-ceph is obsoleted by python-rados, but obsoleting package does not pro...
- We actually are setting `@check_obsoletes@`, as the log shows. However, we might be hitting this:
http://tracker.cep... - 03:44 PM Revision b34b72ba (ceph): Merge pull request #610 from ceph/wip-13393
- Removed rhel distro, fixes #13393 as rhel is not supported in sepia lab
- 03:44 PM devops Bug #13393: Packaging problems in upgrade:giant-x-hammer-distro-basic-vps run
- Removed RHEL from yaml config https://github.com/ceph/ceph-qa-suite/pull/610
- 03:20 PM devops Bug #13393 (Closed): Packaging problems in upgrade:giant-x-hammer-distro-basic-vps run
- We still don't have a way to support RHEL in sepia.
- 03:41 PM Revision 4970b19f (ceph): Removed rhel distro, fixes #13393 as rhel is not supported in sepia lab
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 03:39 PM Revision e6927737 (ceph): rgw: add support for skipping manifest parsing during GET on Swift object.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 01:44 PM Revision 50a2a80f (ceph): suites/fs: test ceph-fuse with libcephfs permission check
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 01:24 PM Revision a52383d0 (ceph): client: don't mark_down on command reply
- I guess this was handy when issuing single commands
from the CLI, but it breaks things badly when
trying to issue com... - 01:23 PM devops Backport #13413: fedora21 has junit, not junit4
- Loic, can you confirm that this backport will/should resolve this build failure in Fedora 22? http://gitbuilder.sepia...
- 01:21 PM devops Backport #13413 (In Progress): fedora21 has junit, not junit4
- 01:16 PM devops Backport #13413 (Resolved): fedora21 has junit, not junit4
- https://github.com/ceph/ceph/pull/6203
- 01:21 PM Revision 415335df (ceph): ceph.spec.in: junit always except for EPEL 6
- The package was renamed a long time ago (around the Fedora 15
timeframe). The "junit4" name is only relevant for EPEL... - 01:16 PM devops Bug #10728: fedora21 has junit, not junit4
- The Fedora 22 gitbuilder is not building firefly-backports because of this.
- 01:14 PM devops Bug #10728 (Pending Backport): fedora21 has junit, not junit4
- 11:57 AM rgw Feature #13412 (New): Multi-range get requests support
- A common functionality in ROOT framework at CERN is to do multi-range get requests. When testing the Huawei cloud sto...
- 11:52 AM Linux kernel client Bug #12538: An image with a long clone chain blows up kernel stack
- @llya Dryomov
Could you indicate more specifically about the submit/callback code? Because from my side I can only... - 08:19 AM Linux kernel client Bug #12538: An image with a long clone chain blows up kernel stack
- Yeah, the stack overflow part was clear from the beginning. Changing the structure of the code so that it doesn't ge...
- 03:02 AM Linux kernel client Bug #12538: An image with a long clone chain blows up kernel stack
- Hello, I'm bo cai, the bug submitter's colleague, I have been focusing on this problem for two weeks and just reached...
- 11:22 AM Revision 7bc06933 (ceph): Merge pull request #6200 from ceph/wip-13364
- mds/Session: use projected parent for auth path check
- 11:08 AM Revision 10bd1cac (ceph): Merge pull request #6116 from jcsp/wip-cephfs-direntry
- pybind/cephfs: fix DirEntry helpers
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:55 AM Stable releases Tasks #11644: firefly v0.80.11
- ...
- 10:16 AM Revision 9db757b8 (ceph): buildpackages: prefer GitbuilderProject.os_{type,version} over config.
- The config['os_type'] and config['os_version'] are not always set for a given
job (for instance, in the rbd suite). W... - 10:16 AM Revision a630da72 (ceph): buildpackages: allow for concurrent build if != sha1
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:56 AM Revision 98769f7c (ceph): Fix casing of Content-Type header
- It turns out, despite the HTTP spec declaring that header field names
should be case-insensitive, some clients treat ... - 08:55 AM Revision 698d75c1 (ceph): tests: robust test for the pool create crushmap test
- The test that goes with f1e86be589803596e86acc964ac5c5c03b4038d8 to
verify that a bugous crush ruleset will prevent t... - 08:53 AM Backport #13410 (In Progress): TEST_crush_rule_create_erasure consistently fails on i386 builder
- 08:53 AM Backport #13410 (Resolved): TEST_crush_rule_create_erasure consistently fails on i386 builder
- https://github.com/ceph/ceph/pull/6201
- 08:52 AM Bug #12419 (Pending Backport): TEST_crush_rule_create_erasure consistently fails on i386 builder
- 06:41 AM rgw Feature #12714: RGW : setting max number of buckets for user via ceph.conf option
- Hammer Backport Tracker : http://tracker.ceph.com/issues/13046
- 06:35 AM Backport #13409 (In Progress): randomize scrub times
- Sage wrote, as an initial comment of the pull request:
This will make hammer users' lives easier by avoiding the b... - 06:35 AM Backport #13409 (Resolved): randomize scrub times
- https://github.com/ceph/ceph/pull/6199
- 06:34 AM Feature #10973 (Pending Backport): randomize scrub times
- 06:31 AM Revision 3c50e4eb (ceph): Merge pull request #6195 from dachary/wip-release-notes
- release-notes: draft v0.94.4 release notes
Reviewed-by: Sage Weil <sage@redhat.com> - 05:15 AM Bug #13408 (Resolved): EOM on hammer-x test with many osds
- 2015-10-07T20:58:26.170 INFO:teuthology.orchestra.run.vpm006.stderr:OSError: librados.so.2: cannot map zero-fill page...
- 04:07 AM Bug #13395 (Resolved): mixed infernalis+hammer crashes on temp object cleanup
- 04:07 AM Revision 6b94b414 (ceph): Merge pull request #6188 from liewegas/wip-13395
- os/FileStore: kludge sloppy hammer temp objects into temp collection
Reviewed-by: David Zafman <dzafman@redhat.com>
... - 04:06 AM Bug #13404 (Duplicate): "Crash: failed to reach quorum.." in upgrade:hammer-x-infernalis-distro-b...
- this was fixed shortly after this run, see #13379
- 03:23 AM Bug #13289: FileStore::mount No close fsid_fd\basedir_fd\current_fd
- @Sage Weil
FileStore::lock_fsid & KeyValueStore::lock_fsid
use l.l_type = F_WRLCK
I'm not sure whether can be ame... - 03:09 AM Revision 0742177c (ceph): osd: use another name for randomize scrub option
- s/osd_scrub_interval_limit/osd_scrub_interval_randomize_ratio/
Fixes: #10973
Signed-off-by: Kefu Chai <kchai@redhat.... - 03:07 AM Revision fad33861 (ceph): osd: randomize scrub times to avoid scrub wave
- - to avoid the scrub wave when the osd_scrub_max_interval reaches in a
high-load OSD, the scrub time is randomized.... - 03:06 AM Revision 9c130336 (ceph): osd: use __func__ in log messages
- Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 0f7f35670f03f3f58329c00d323963710e7e495d) - 03:05 AM Revision 4a3dedff (ceph): osd: simplify OSD::scrub_load_below_threshold() a little bit
- avoid unnecessary comparison
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 2ab0e606dfd2847e... - 02:59 AM Revision 1e57e6de (ceph): mds/Session: use projected parent for auth path check
- In particular, a file's current path might indicate no parent
because the initial link into the tree isn't committed ... - 02:51 AM Revision 4014e319 (ceph): common: perf counter for bufferlist history total alloc
- this is useful for tracking how many bytes malloc at bufferlist
Signed-off-by: Xinze Chi <xinze@xsky.com> - 02:51 AM Revision a1f19678 (ceph): tests: add test for history alloc counter in bufferlist
- Signed-off-by: Xinze Chi <xinze@xsky.com>
- 01:30 AM rbd Bug #13396 (Resolved): use after free of cct in ObjectCacher::flusher
- This was only an issue with the backport.
It should be fixed in https://github.com/ceph/ceph/pull/6097 now, with t... - 12:25 AM Revision 116bc832 (ceph): ceph_test_libcephfs: parse env properly (access)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:25 AM Revision 94893593 (ceph): ceph_test_libcephfs: parse CEPH_ARGS properly
- This has to happen after the config parse.
Signed-off-by: Sage Weil <sage@redhat.com>
10/07/2015
- 11:35 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. rbd...
- 11:32 PM Stable releases Tasks #13356: hammer v0.94.6
- ...
- 10:42 PM Revision 24268cf4 (ceph): librbd: invoking RBD::open twice will leak memory
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit a5e88fcf11ebb16d4a1405b21cf6f895b37f185e) - 10:40 PM Revision 21236ac3 (ceph): release-notes: draft v0.94.4 release notes
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 10:28 PM Backport #13407 (Resolved): tests: qa/workunits/cephtool/test.sh: don't assume crash_replay_inter...
- https://github.com/ceph/ceph/pull/6172
- 10:27 PM Bug #13406 (Resolved): tests: qa/workunits/cephtool/test.sh: don't assume crash_replay_interval=45
- e.g., it's 5 in teuthology's ceph.conf.
https://github.com/ceph/ceph/pull/6098 - 10:18 PM CephFS Bug #13364: LibCephFS locking tests are failing and/or lockdep asserting
- Run: http://pulpito.ceph.com/teuthology-2015-10-07_05:00:08-smoke-master-distro-basic-multi/
Logs: http://qa-proxy.c... - 10:10 PM Bug #13400 (Resolved): mon: fix crush testing for new pools
- 03:15 PM Bug #13400 (Resolved): mon: fix crush testing for new pools
- only test the relevant ruleset
https://github.com/ceph/ceph/pull/5979
- 10:09 PM Backport #13401 (Resolved): mon: fix crush testing for new pools
- 04:39 PM Backport #13401: mon: fix crush testing for new pools
- Verify that the bug shows at least once every 20 job. Running on giant-x because infernalis changes more often.
<p... - 03:17 PM Backport #13401 (In Progress): mon: fix crush testing for new pools
- 03:17 PM Backport #13401 (Resolved): mon: fix crush testing for new pools
- https://github.com/ceph/ceph/pull/6192
- 10:09 PM Revision 70e612a3 (ceph): Merge pull request #6192 from dachary/wip-13401-hammer
- mon: fix crush testing for new pools
Reviewed-by: Sage Weil <sage@redhat.com> - 09:38 PM devops Bug #13393: Packaging problems in upgrade:giant-x-hammer-distro-basic-vps run
- Some things stand out to me:
1) This is testing upgrades to/from giant. Do we want to keep doing that, now that Gi... - 09:13 PM rbd Bug #13405 (In Progress): rbd-replay-prep trace output is not version controlled
- 08:57 PM rbd Bug #13405 (Resolved): rbd-replay-prep trace output is not version controlled
- It's currently not possible to safely change the format of the trace output (i.e. to add new fields, handle new IO ev...
- 08:58 PM CephFS Bug #13256 (Resolved): I/O error with cephfs accessing root .snap directory on v9.0.3
- 08:57 PM CephFS Bug #13256: I/O error with cephfs accessing root .snap directory on v9.0.3
- 08:56 PM rbd Bug #13384 (Fix Under Review): rbd-replay-prep stack overflow while converting 'rbd bench-write' ...
- 08:54 PM rbd Bug #13384: rbd-replay-prep stack overflow while converting 'rbd bench-write' trace
- *infernalis PR*: https://github.com/ceph/ceph/pull/6194
- 08:56 PM rbd Bug #13378 (Fix Under Review): rbd-replay-prep requires >4 hrs to convert 'rbd bench-write' trace
- 08:55 PM rbd Bug #13378: rbd-replay-prep requires >4 hrs to convert 'rbd bench-write' trace
- *infernalis PR*: https://github.com/ceph/ceph/pull/6194
- 08:55 PM rbd Bug #13325 (Fix Under Review): rbd-replay-prep doesn't handle new IO APIs
- 08:55 PM rbd Bug #13325: rbd-replay-prep doesn't handle new IO APIs
- *infernalis PR*: https://github.com/ceph/ceph/pull/6194
- 08:55 PM rbd Bug #13221 (Fix Under Review): rbd-replay: cryptic error when 'rbd' pool does not exist
- *infernalis PR*: https://github.com/ceph/ceph/pull/6194
- 08:55 PM rbd Bug #13220 (Fix Under Review): rbd-replay-prep: crashes on incorrect trace file
- *infernalis PR*: https://github.com/ceph/ceph/pull/6194
- 08:51 PM Revision 646e50a7 (ceph): rbd-replay-prep: added --verbose command line option
- This new command-line will dump all the processed events as they
are extracted from the trace file.
Signed-off-by: J... - 08:40 PM Revision 547caa84 (ceph): tasks/cephfs: fix mount_timeout config loading
- Previously were defaulting to a string, which
always compared greater than elapsed, so never
timed out.
Fixes: #1282... - 08:34 PM Revision 98f513a1 (ceph): rbd-replay-prep: stream events to the prep file
- Avoid building the entire prep event history in memory before
attempting to write the prepped trace file.
Signed-off... - 08:34 PM Revision 65fb1b86 (ceph): rbd-replay-prep: simplify IO dependency calculation
- Only track read-after-write and write-after-write IO dependencies
via the associated write completions. All IO event... - 08:22 PM Bug #11142: "Exception: ceph-objectstore-tool: import failure" in upgrade:firefly-x-hammer-distro...
- Same in run:
http://pulpito.ceph.com/teuthology-2015-10-07_10:51:15-upgrade:firefly-firefly-distro-basic-vps/
Logs:... - 07:41 PM Revision a1e99f06 (ceph): rbd-replay-prep: avoid using assert statements on user inputs
- Fixes: #13220
Backport: hammer
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 07:41 PM Revision b5b4a9dd (ceph): rbd-replay-prep: support new read/write APIs
- Added support for read2, write2, aio_read2, and aio_write2 APIs.
Fixes: 13325
Backport: hammer
Signed-off-by: Jason ... - 07:41 PM Revision 4f436e10 (ceph): rbd-replay: improve error messages
- Fixes: #13221
Backport: hammer
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 07:27 PM Revision ca5c0051 (ceph): Merge pull request #589 from ceph/wip-ecpool-s3test
- s3tests using ec data pool for smoke
- 06:33 PM rgw Bug #13197 (Rejected): rgw: creating user by admin api returns 403 access deny
- 05:09 PM rgw Bug #13197: rgw: creating user by admin api returns 403 access deny
- Got it
I passed uid and display-name in data instead of params.
I add the missing params to url, like this http://{... - 05:56 PM Revision 84903b32 (ceph): Merge branch 'infernalis'
- 05:55 PM Revision 94d54f75 (ceph): Merge remote-tracking branch 'origin/wip-vstart-runner' into infernalis
- Reviewed-by: Greg Farnum <gfarnum@redhat.com>
- 05:52 PM Revision 1a421975 (ceph): Merge pull request #6170 from jcsp/wip-spurious-warning
- mds: avoid emitting cap warnings before evicting session
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 05:51 PM Revision d73c0998 (ceph): Merge pull request #6128 from jcsp/wip-snapserver-crash
- mds: fix SnapServer crash on deleted pool
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 05:47 PM Revision 05b0c781 (ceph): Merge branch 'wip-yrf-fix1' of git://github.com/H3C/ceph into infernalis
- Reviewed-by: Greg Farnum <gfarnum@redhat.com>
- 05:46 PM Bug #13369 (Duplicate): "librados/TestCase.cc:216: Failure" in upgrade:firefly-hammer-x:parallel-...
- duplicate of #13401
- 05:45 PM Revision 6aac3122 (ceph): Merge branch 'wip-13256' of git://github.com/ukernel/ceph into infernalis
- Reviewed-by: Greg Farnum <gfarnum@redhat.com>
- 05:44 PM Revision 858059ed (ceph): qa: avoid using sudo in fsstress
- This test required root in order to copy its built
binary into /usr (presumably to avoid rebuilding it).
That's not ... - 05:25 PM Bug #13404 (Duplicate): "Crash: failed to reach quorum.." in upgrade:hammer-x-infernalis-distro-b...
- Run: http://pulpito.ceph.com/teuthology-2015-10-06_17:10:09-upgrade:hammer-x-infernalis-distro-basic-vps/
Jobs: ['10... - 05:09 PM Revision 52ef6175 (ceph): Merge pull request #6186 from ceph/wip-12913-2
- cls_rgw: fix bucket listing when dealing with invisible entries
- 05:07 PM rbd Bug #13371: "[ FAILED ] LibRBD.*" tests in upgrade:firefly-hammer-x:stress-split-infernalis-dis...
- Run: http://pulpito.ceph.com/teuthology-2015-10-07_08:53:35-upgrade:firefly-hammer-x:stress-split-infernalis-distro-b...
- 04:40 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- Note to Yuri From Boris IRC chat:...
- 09:45 AM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- I've created a rhel bugzilla for the yum-plugin-priorities issue:
https://bugzilla.redhat.com/show_bug.cgi?id=1269... - 04:38 PM Bug #13403 (Rejected): Error running "mkfs.xfs" in upgrade:hammer-x-infernalis-distro-basic-multi...
- Run: http://pulpito.ceph.com/teuthology-2015-10-04_17:02:02-upgrade:hammer-x-infernalis-distro-basic-multi/
Jobs: ['... - 04:30 PM rgw Documentation #13317: ERROR: invalid flag --lazy-remove
- Thanks Yehuda and Nathan !
- 04:27 PM Revision 5716f5f1 (ceph): smoke/basic/tasks/libcephfs: fix client debug override
- Also debug mds
Signed-off-by: Sage Weil <sage@redhat.com> - 04:12 PM Bug #13279 (Duplicate): upgrade suite: pool_create failed with error -4 EINTR
- Duplicate of http://tracker.ceph.com/issues/13401
- 03:05 PM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- We want
* https://github.com/ceph/ceph/commit/aa238e5ed50f44a94caf84567267e4f6be8732a2
* https://github.com/cep... - 02:37 PM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- Because of the crush ruleset validation introduced by https://github.com/ceph/ceph/pull/5276 in hammer September 6th,...
- 02:11 PM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- In the hammer "upgrade/giant-x install":https://github.com/ceph/ceph-qa-suite/blob/hammer/suites/upgrade/giant-x/para...
- 01:41 PM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- First occurrence with the tests involving the infernalis branch September 13, 2015....
- 01:35 PM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- Nothing significant was merged in the hammer ceph-qa-suite branch before the problems started showing up. The giant-x...
- 01:22 PM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- The following can't be the cause because it allows pool deletion by default and no ceph-qa-suite branch changes that....
- 01:16 PM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- ...
- 01:12 PM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- On the teuthology machine, in the /a directory,...
- 12:57 PM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- The bug was fist seen early september, shortly after the following commits were merged in the hammer branch:...
- 10:46 AM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- Older similar failures:
* "upgrade:firefly-x/stress-split/{0-cluster/start.yaml 1-firefly-install/firefly.yaml 2-p... - 04:09 PM Revision 2a281140 (ceph): crush/CrushTester: test fewer inputs when running crushtool
- If there are a lot of crush rules (say, 100) then the test can
take a long time. 100 values per rule should be enoug... - 04:09 PM Revision 25bd2778 (ceph): mon/OSDMonitor: fix crush injection error message
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 1b3090d50e5bd5ca3e6e396b23d2d9826896c718)
Conf... - 04:09 PM Revision abc5b5f1 (ceph): tests: update to match crushmap validation message
- http://tracker.ceph.com/issues/13182 Fixes: #13182
Signed-off-by: Loic Dachary <ldachary@redhat.com>
(cherry picked ... - 04:09 PM Revision 6635530a (ceph): mon/OSDMonitor: only test crush ruleset for the newly created pool
- Otherwise, we test *all* crush rules.. which might be a lot, and
which is a big waste of time and effort.
Signed-off... - 03:49 PM Revision e049de34 (ceph): os/FileStore: kludge sloppy hammer temp objects into temp collection
- When we are running with a mixed hammer cluster, hammer primaries
will generate temp object names that are sloppy. M... - 03:47 PM Revision 96aabe76 (ceph): ceph.spec.in: move BuildRequires out of subpackages
- Since the main package and all the subpackages are built in the
same environment, concentrate all the BuildRequires i... - 03:47 PM Revision 5a11d761 (ceph): ceph.spec.in: move python-sphinx BuildRequires to the right section
- These belong in the section for distro-conditional dependencies.
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 03:37 PM Revision cc1fedda (ceph): crush/CrushTester: allow testing by ruleset
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit aa238e5ed50f44a94caf84567267e4f6be8732a2)
Conf... - 03:35 PM devops Cleanup #13402: ceph.spec.in: MY_CONF_OPT is a holdover from the past
- infernalis PR: https://github.com/ceph/ceph/pull/6190
- 03:31 PM devops Cleanup #13402 (Resolved): ceph.spec.in: MY_CONF_OPT is a holdover from the past
- The variable ...
- 03:32 PM Revision d258bf58 (ceph): ceph.spec.in: drop MY_CONF_OPTS
- http://tracker.ceph.com/issues/13402 Fixes: #13402
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 03:13 PM Fix #12953: mon: cull / scrub unused crush rules when pools are deleted
- 03:06 PM Bug #13382 (Pending Backport): osd/PG.cc: 758: FAILED assert(info.history.same_interval_since == ...
- 03:06 PM Revision 1d4df5d3 (ceph): Merge pull request #6185 from liewegas/wip-13382
- osd/PG: fix generate_past_intervals
Reviewed-by: David Zafman <dzafman@redhat.com> - 03:02 PM Bug #13399 (Closed): 2015-10-06 09:55:10.883565 mon.0 10.214.131.14:6789/0 61 : cluster [WRN] ...
- 02:18 PM Bug #13398 (Closed): leveldb compaction error
- leveldb compaction on mount causes a segmentation fault
seems related to this pull request (github.com/ceph/ceph/p... - 12:42 PM devops Bug #13353: ceph_selinux manpage is made even when selinux is not being built
- Works great in SUSE, i.e. with ...
- 08:31 AM devops Bug #13353: ceph_selinux manpage is made even when selinux is not being built
- Testing Boris's PR now.
- 05:26 AM Bug #13289 (In Progress): FileStore::mount No close fsid_fd\basedir_fd\current_fd
- 02:46 AM Bug #13289: FileStore::mount No close fsid_fd\basedir_fd\current_fd
- huanwen ren wrote:
> Sage Weil wrote:
> > sure.. submit a pr to change it to O_RDONLY?
>
> Thanks for your reply... - 02:45 AM Bug #13289: FileStore::mount No close fsid_fd\basedir_fd\current_fd
- In our environment, there have been fsid was changed, see:
http://tracker.ceph.com/issues/13257 - 02:39 AM Bug #13289: FileStore::mount No close fsid_fd\basedir_fd\current_fd
- Sage Weil wrote:
> sure.. submit a pr to change it to O_RDONLY?
Thanks for your reply
I submit changes:https:/... - 05:08 AM rbd Bug #13396: use after free of cct in ObjectCacher::flusher
- Doesn't seem to be reproducing on hammer, though I don't see any suspicious changes in hammer-backports. I'm guessing...
- 04:37 AM rbd Bug #13396: use after free of cct in ObjectCacher::flusher
- reproduced the first time on hammer-backports, trying against plain hammer
- 03:35 AM rbd Bug #13396 (Resolved): use after free of cct in ObjectCacher::flusher
- So far only seen in hammer-backports, so it may be an issue with a backport. Trying to reproduce now.
This is the ... - 02:44 AM Bug #13257: Osd fsid file has been tampered with
- but Disk error does not affect the osd
After I remove fsid exception logging information, osd.60 can normal boot
- 02:26 AM Bug #13395 (Fix Under Review): mixed infernalis+hammer crashes on temp object cleanup
- https://github.com/ceph/ceph/pull/6188
- 02:13 AM Bug #13395 (Resolved): mixed infernalis+hammer crashes on temp object cleanup
- ...
- 12:52 AM Bug #13379 (Resolved): crash in waitlist_or_zap_client
- 12:51 AM Revision 7e8432a2 (ceph): Merge pull request #6182 from liewegas/wip-13379
- mon: do not remove proxied sessions
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
10/06/2015
- 09:44 PM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- Loic I see similar in run, assuming a dupe for now:
http://pulpito.ceph.com/teuthology-2015-10-05_17:05:09-upgrade:g... - 02:22 PM Bug #13279 (In Progress): upgrade suite: pool_create failed with error -4 EINTR
- 09:35 PM devops Bug #13393 (Closed): Packaging problems in upgrade:giant-x-hammer-distro-basic-vps run
- Run: http://pulpito.ceph.com/teuthology-2015-10-05_17:05:09-upgrade:giant-x-hammer-distro-basic-vps/
Jobs: ['1089914... - 09:28 PM Bug #13390: Error "ceph osd pool create unique_pool_1 16" in upgrade:firefly-x-hammer-distro-basi...
- Also in giant-x/hammer
Run: http://pulpito.ceph.com/teuthology-2015-10-05_17:05:09-upgrade:giant-x-hammer-distro-bas... - 09:00 PM Bug #13390 (Won't Fix): Error "ceph osd pool create unique_pool_1 16" in upgrade:firefly-x-hammer...
- Run: http://pulpito.ceph.com/teuthology-2015-10-05_17:18:01-upgrade:firefly-x-hammer-distro-basic-vps/
Jobs: ['10899... - 09:20 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- @Ken: Do they use it with rhel 7.0 or rhel 7.1? If they use rhel 7.1, there should be no change to the packages they ...
- 09:09 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- ...
- 08:51 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- Ken Dreyer wrote:
> We should stop appending with "tee -a" ... it ends up writing the same line to the file many tim... - 08:49 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- OK, the actual issue here is a bug in yum-plugin-priorities. The way it works now is that it won't exclude older vers...
- 08:27 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- Some checks we did with branto and he was able to reproduce it locally....
- 04:14 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- We should stop appending with "tee -a" ... it ends up writing the same line to the file many times, and last I rememb...
- 04:08 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- Boris Ranto wrote:
> @Vasu: The issue here still seems to be that the 'check_obsoletes = 1' is not set, see few line... - 03:59 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- @Vasu: The issue here still seems to be that the 'check_obsoletes = 1' is not set, see few lines above those messages...
- 01:13 AM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- yuri,
this seems different to me,... - 01:04 AM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- Ken,
I somehow think this is a test issue, when testing with CentOS/Fedora in mixed cluster mode, I think upgrade ... - 09:09 PM Bug #13391 (Closed): Errors running "rbd/test_librbd.sh" in upgrade:firefly-x-hammer-distro-basic...
- Run: http://pulpito.ceph.com/teuthology-2015-10-05_17:18:01-upgrade:firefly-x-hammer-distro-basic-vps/
Jobs: ['10899... - 08:49 PM Revision 30eebbd7 (ceph): Merge remote-tracking branch 'gh/infernalis'
- Conflicts:
suites/upgrade/hammer-x/point-to-point-x/point-to-point.yaml - 08:46 PM Revision 21cefaf2 (ceph): upgrade/hammer-x/point-to-point: whitelist wrongly marked me down
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:58 PM Bug #13381: osd/SnapMapper.cc: 282: FAILED assert(check(oid)) on hammer->jewel upgrade
- Sage Weil wrote:
> I think this is just cruft from something that happened ages ago.
2015-04-29 03:23:54.774958, ... - 04:58 PM Bug #13381: osd/SnapMapper.cc: 282: FAILED assert(check(oid)) on hammer->jewel upgrade
- I think this is just cruft from something that happened ages ago.
- 03:19 PM Bug #13381: osd/SnapMapper.cc: 282: FAILED assert(check(oid)) on hammer->jewel upgrade
- same assert was triggering several days before the infernalis upgrade, so this is nothing new.
- 03:19 PM Bug #13381: osd/SnapMapper.cc: 282: FAILED assert(check(oid)) on hammer->jewel upgrade
- looks like an object is in the wrong directory...
- 03:09 PM Bug #13381 (Won't Fix): osd/SnapMapper.cc: 282: FAILED assert(check(oid)) on hammer->jewel upgrade
- ...
- 07:47 PM rgw Documentation #13317 (In Progress): ERROR: invalid flag --lazy-remove
- *infernalis PR* https://github.com/ceph/ceph/pull/6187
- 06:28 PM rgw Documentation #13317: ERROR: invalid flag --lazy-remove
- The --lazy-remove flag has been removed over 3 years ago. Docs need to be updated.
- 07:44 PM Revision 468c2dd6 (ceph): doc: remove mention of --lazy-remove from radosgw-admin manpage
- "The --lazy-remove flag has been removed over 3 years ago. Docs need to be
updated."
http://tracker.ceph.com/issues/... - 07:21 PM rbd Backport #13388 (Rejected): librbd: reads larger than cache size hang
- 07:20 PM rbd Backport #13387 (Resolved): librbd: reads larger than cache size hang
- https://github.com/ceph/ceph/pull/6354
- 06:38 PM rgw Bug #13197: rgw: creating user by admin api returns 403 access deny
- The request is missing params, e.g., uid=, display-name=, etc.
It looks like the caps actually are configured correc... - 06:35 PM Revision 98cbf038 (ceph): osd/PG: fix generate_past_intervals
- We may be only calculating older past intervals and have a valid
history.same_interval_since value, in which case the... - 06:32 PM Revision 5e9cf8e3 (ceph): doc/release-notes: fix math error in firefly notes
- Reported-by: Christopher Kunz <chris@filoo.de>
Signed-off-by: Sage Weil <sage@redhat.com> - 06:32 PM rgw Bug #13241 (Duplicate): radosgw-admin assertion error: rgwlog['bucket'].find(bucket_name) == 0 o...
- Probably duplicate of one 13242, if happens again please reopen.
- 06:30 PM rgw Bug #13242 (Duplicate): rgw_readwrite: md5sum check failed original hash: �6�����:ï...
- Probably duplicate of 13240
- 06:27 PM rgw Bug #13326 (Resolved): rgw: objexp collector should specially treat ENOENT on reading bucket info
- Was merged in commit:
79d8f895a5bab7a52ca3132823614c0bd7bc1617 - 06:23 PM rgw Bug #12958 (Fix Under Review): rgw: orphan tool should be careful about removing head objects
- pr #6044
- 06:21 PM rgw Bug #12890 (Fix Under Review): rgw: the swift key remains after removing a subuser
- https://github.com/ceph/ceph/pull/6002
- 06:19 PM rgw Bug #12819 (Resolved): rgw: objects starting with underscore in bucket with versioning enabled ar...
- Merged in commit:f1ead76f80cc3d078778080c35a6427256874062
- 06:18 PM rgw Bug #12955: Setting ACL on Object removes ETag
- 10981
- 06:16 PM rgw Bug #12955 (Fix Under Review): Setting ACL on Object removes ETag
- 06:15 PM rgw Bug #12661 (Duplicate): radosgw-agent datasync S3ResponseError: 403 Forbidden dest_connection.get...
- Duplicate of #13239
- 06:13 PM rgw Bug #12913 (Fix Under Review): rgw: bucket listing hangs on versioned buckets
- PR http://github.com/ceph/ceph/pull/6186
- 06:11 PM Bug #13359: giant stale requests
- I think this is a bug in giant. There seem to be some old requests stuck in the op tracker which I think actually co...
- 05:42 PM Bug #13359: giant stale requests
- I think /a/loic-2015-10-05_01:41:20-upgrade:hammer-hammer-backports---basic-vps/1088508/remote is the actual path -- ...
- 06:03 PM RADOS Bug #13385 (Need More Info): cephx: verify_authorizer could not decrypt ticket info: error: NSS A...
- 05:48 PM RADOS Bug #13385: cephx: verify_authorizer could not decrypt ticket info: error: NSS AES final round fa...
- ...
- 05:39 PM RADOS Bug #13385: cephx: verify_authorizer could not decrypt ticket info: error: NSS AES final round fa...
- Well, the rotating keyring used for authenticating is protected by a Mutex, but it hands out a reference, so it's pre...
- 05:22 PM RADOS Bug #13385: cephx: verify_authorizer could not decrypt ticket info: error: NSS AES final round fa...
- SEC_ERROR_BAD_DATA -8190 Security library: received bad data....
- 05:03 PM RADOS Bug #13385 (Can't reproduce): cephx: verify_authorizer could not decrypt ticket info: error: NSS ...
- Dan saw thing on bigbang, too....
- 06:00 PM CephFS Bug #13364: LibCephFS locking tests are failing and/or lockdep asserting
- 05:56 PM Bug #13276 (Duplicate): *** Caught signal (Segmentation fault) ** in upgrade:hammer-x-infernalis-...
- 05:28 PM Bug #13386 (Can't reproduce): heartbeat check failed due to hang processing copy_from (hammer)
- http://pulpito.ceph.com/loic-2015-10-03_11:11:28-rados-wip-pr-5887---basic-multi/1086356
The osd crashed due to
... - 05:02 PM rbd Bug #13384 (Resolved): rbd-replay-prep stack overflow while converting 'rbd bench-write' trace
- Appears to be a chain of "rbd_replay::AioWriteIO" objects, resulting in a long chain of shared pointer destructors be...
- 04:50 PM Bug #13383 (Can't reproduce): import/export screws up same_interval_since
- before the export:...
- 04:44 PM devops Bug #13352 (Resolved): RPM: default g++ garbage collection settings need tweaking on some machines
- The patch was merged to infernalis branch.
- 04:43 PM devops Bug #13324 (Resolved): run-make-check.sh fails on SLE-12 (needs %bcond_with selinux)
- The patches were merged to infernalis branch.
- 04:42 PM devops Bug #13346 (Resolved): ceph %post scriptlet assumes existence of user/group created by a differen...
- The patch was merged to infernalis branch.
- 04:39 PM devops Bug #13353: ceph_selinux manpage is made even when selinux is not being built
- This should be fixed by: https://github.com/ceph/ceph/pull/6183
- 04:39 PM Bug #13382: osd/PG.cc: 758: FAILED assert(info.history.same_interval_since == same_interval_since)
- https://github.com/ceph/ceph/pull/6185
- 04:38 PM Bug #13382 (Resolved): osd/PG.cc: 758: FAILED assert(info.history.same_interval_since == same_int...
- ...
- 04:36 PM rbd Bug #13372 (Fix Under Review): librbd: object map invalid but not flagged as such
- *infernalis PR*: https://github.com/ceph/ceph/pull/6184
- 02:36 PM rbd Bug #13372: librbd: object map invalid but not flagged as such
- Related to OSD issue: #13380
- 02:20 PM rbd Bug #13372: librbd: object map invalid but not flagged as such
- The lock is held by the OSD!...
- 12:43 PM rbd Bug #13372 (In Progress): librbd: object map invalid but not flagged as such
- 12:12 AM rbd Bug #13372 (Resolved): librbd: object map invalid but not flagged as such
- http://pulpito.ceph.com/teuthology-2015-10-03_23:00:08-rbd-infernalis-distro-basic-multi/1087438/
Reproduced by ru... - 04:31 PM Revision e675400d (ceph): librbd: invalidate object map on error even w/o holding lock
- If there is a deep bug that prevents the object map from owning
the lock before objects are updated, flag the object ... - 04:08 PM Revision 378d56d1 (ceph): man/Makefile-server.am: conditionalize make ceph_selinux manpage
- http://tracker.ceph.com/issues/13353 Fixes: #13353
Modified-by: Boris Ranto <branto@redhat.com>
Signed-off-by: Natha... - 04:08 PM Revision bc48ef0f (ceph): selinux: Fix man page location
- The SELinux man page was previously located in two places and the man
page that was supposed to be updated when rgw s... - 04:05 PM Revision e5a6529a (ceph): Merge pull request #6171 from SUSE/wip-infernalis-obs
- Get infernalis to build in openSUSE Build Service
Reviewed-by: Boris Ranto <branto@redhat.com> - 03:46 PM rbd Bug #13164 (Pending Backport): librbd: reads larger than cache size hang
- 03:45 PM rbd Bug #13304 (In Progress): "TestLibRBD.Metadata , TestLibRBD.UpdateFeatures" tests failed in upgra...
- 03:32 PM rbd Bug #13221 (In Progress): rbd-replay: cryptic error when 'rbd' pool does not exist
- 03:31 PM rbd Bug #13378 (In Progress): rbd-replay-prep requires >4 hrs to convert 'rbd bench-write' trace
- 12:30 PM rbd Bug #13378 (Resolved): rbd-replay-prep requires >4 hrs to convert 'rbd bench-write' trace
- perf top indicates all the time is being spent calculating IO dependencies.
- 03:11 PM Revision 06508624 (ceph): Merge pull request #5887 from Abhishekvrshny/wip-13044-hammer
- LibCephFS.GetPoolId failure
Reviewed-by: Sage Weil <sage@redhat.com> - 02:58 PM Bug #13058: Ceph destroyed my MBR record when trying to convert it to GPT after initiating a new ...
- By providing the whole disk as a journal (/dev/sda) you allowed ceph-disk to use it entirely. This should work fine w...
- 02:54 PM Revision fb50ff62 (ceph): mon: do not remove proxied sessions
- A proxied session (see handle_forward) isn't registered, so it doesn't
need remove_session. Moreover, s->con is null... - 02:51 PM Bug #13080 (Rejected): python-rados in PyPI / with python3 ?
- Rejecting this one for now, feel free to re-open another with a specific bug or feature request. Thanks !
- 02:48 PM Bug #13238 (Won't Fix): duplicate start of ceph-osd daemon
- I believe this misbehavior has been fixed in Hammer and would be resolved by upgrading the OSDs. Marking this problem...
- 02:47 PM Bug #13323 (Resolved): test.sh: osd/ReplicatedPG.cc: 8851: FAILED assert(head_obc)
- happens due ot proxy write.. shouldn't affect hammer.
- 02:47 PM Bug #13323 (Pending Backport): test.sh: osd/ReplicatedPG.cc: 8851: FAILED assert(head_obc)
- 02:26 PM Bug #13323 (Fix Under Review): test.sh: osd/ReplicatedPG.cc: 8851: FAILED assert(head_obc)
- 02:26 PM Bug #13323: test.sh: osd/ReplicatedPG.cc: 8851: FAILED assert(head_obc)
- https://github.com/ceph/ceph/pull/6181
- 02:47 PM RADOS Bug #13329: EUCLEAN (117) from xfs is very bad (should crash just like EIO)
Correction: It would be better to ignore filestore_fail_eio if we get this error, just crash.
There is a questio...- 02:44 PM Revision 4f54a0dd (ceph): Merge pull request #6181 from athanatos/wip-13323
- ReplicatedPG: consider IGNORE_CACHE for all maybe_handle_cache calls
Reviewed-by: Sage Weil <sage@redhat.com> - 02:42 PM Backport #13354 (Resolved): tests: do not assume crash_replay_interval 45
- 02:40 PM Bug #13289: FileStore::mount No close fsid_fd\basedir_fd\current_fd
- sure.. submit a pr to change it to O_RDONLY?
- 02:39 PM Bug #13280 (Duplicate): "FAILED assert(head_obc)" in smoke-master-distro-basic
- 02:36 PM Bug #13349 (Resolved): "[WRN] failed to encode map e2314 with expected crc".." in upgrade:hammer-...
- 02:35 PM Bug #13110 (Resolved): osd: should accept delete op when full
- fixed in infernalis.. there is a librados flag to send ios despite the full flag.
no tools use it yet... - 02:34 PM Bug #9746 (Resolved): reconcile upstream ceph.spec.in with other ceph.spec (SuSE, EPEL, etc)
- Given the increased contributions to ceph.spec.in and the mix of SUSE + RedHat + CentOS changes / conditions, I assum...
- 02:32 PM Bug #13380 (Resolved): Proxied write of lock.lock class method results in incorrect locker
- When a "lock.lock" class method is proxied, the end result is that the OSD is listed as the locker instead of the cli...
- 02:29 PM Bug #13258 (Need More Info): osd Take turns to the down ("FAILED assert(0 == "unexpected error")")
- 02:28 PM Bug #13216 (Duplicate): import/export bug: ceph_test_rados read incorrect buffer
- 02:21 PM Bug #13369 (In Progress): "librados/TestCase.cc:216: Failure" in upgrade:firefly-hammer-x:paralle...
- 02:19 PM Bug #13379 (Resolved): crash in waitlist_or_zap_client
- ...
- 02:19 PM CephFS Support #13267 (Closed): mds heap stats cause warn message but working
- Unless there are other symptoms, this log warning is not a problem. It's an indication that a client disconnected, wh...
- 01:27 PM Revision be3c4a81 (ceph): mds: implement filtered "session ls" tell command
- So that one can efficiently query client session
state remotely.
Signed-off-by: John Spray <john.spray@redhat.com> - 01:27 PM Revision 0d1cab43 (ceph): test: add TestSessionFilter
- Tests for SessionFilter, the class filters
allows session listing and eviction in the
new MDS tell commands.
Signed-... - 01:27 PM Revision 4af17646 (ceph): mds: add auth_name to session_info_t
- Record the name of the entity who's authorisation
credentials were used during connection. This
allows us to refer t... - 01:27 PM Revision 47a1816e (ceph): mds: call through to MDSRank in handle_command
- ...so that we can implement things like
session ls in MDSRankDispatcher.
Signed-off-by: John Spray <john.spray@redha... - 01:18 PM Revision 800d9746 (ceph): ceph.spec.in: enable OBS post-build-checks to find systemd-tmpfiles
- The openSUSE Build Service runs a number of "post-build checks" after the RPMs
have been generated. One of these test... - 01:18 PM Revision 10452915 (ceph): ceph.spec.in: remove comments regarding ceph UID/GID in SUSE
- It is possible that the ceph user/group will not have fixed UID/GID in SUSE.
Instead, it is possible that the ceph pa... - 01:18 PM Revision 498578db (ceph): etc/sysconfig/ceph: add CEPH_AUTO_RESTART_ON_UPGRADE
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 01:18 PM Revision f8895fc7 (ceph): ceph.spec.in: Standardize systemd preun and postun scripts
- Currently, the main ceph package and the ceph-radosgw behave
differently on upgrade. This commit unifies their behavi... - 12:40 PM Revision 9e226a80 (ceph): ceph.spec.in: use %fillup_only macro in SLE/openSUSE
- SUSE does not allow /etc/sysconfig/ceph to be owned by the ceph
package.
Signed-off-by: Nathan Cutler <ncutler@suse.... - 12:40 PM Revision 5dd93d7d (ceph): ceph.spec.in: selinux by default on RHEL/Fedora, non-default on SUSE
- Surround it with an appropriate conditional.
http://tracker.ceph.com/issues/13324 Fixes: #13324
Signed-off-by: Nath... - 12:40 PM Revision 32178037 (ceph): Revert "install-deps.sh: use %bcond_with selinux on SLE/openSUSE"
- This reverts commit 1df2cc2bf625a1f65ef4968d9cf313cc8ee9acc5.
- 12:40 PM Revision db4727f9 (ceph): ceph.spec.in: Use _smp_mflags instead of _NPROCESSORS_ONLN
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 12:40 PM Revision 404ffab7 (ceph): ceph.spec.in: fix for out-of-memory errors in OBS
- Add "--param ggc-min-expand=20 --param ggc-min-heapsize=32768"
to RPM_OPT_FLAGS, ensuring gcc does not add debug symb... - 12:40 PM Revision 2c6977cd (ceph): ceph.spec.in: distro-conditional groupadd and useradd
- The -o option to groupadd/useradd is not recognized in SLE12. For
SLE/openSUSE, follow the openSUSE packaging guideli... - 12:40 PM Revision 0dd93136 (ceph): ceph.spec.in: move systemd-tmpfiles stuff to ceph-common
- Since the ceph user and group are created in the ceph-common
%pre scriptlet, the systemd-tmpfiles --create command ne... - 12:33 PM Revision d58d885d (ceph): ceph.spec.in: remove SUSE-specific curses hack
- Unclear what this was supposed to fix.
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 12:31 PM rgw Bug #13377: radosgw-agent[ERROR ] RegionMapError: Could not retrieve region map from destination:...
- This affects all versions of the radosgw-agent that have a very old version of boto available.
The old versions ha... - 12:22 PM rgw Bug #13377 (Resolved): radosgw-agent[ERROR ] RegionMapError: Could not retrieve region map from d...
- python-boto 2.3.0.1
2015-10-06 14:19:41,689 16628 [radosgw_agent.client][INFO ] creating connection to endpoint: ... - 10:34 AM Revision 50567b49 (ceph): ceph.spec.in: drop %insserv_prereq (obsoleted by systemd)
- The %post, etc. scriptlets are no longer calling %insserv, et al.
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 10:34 AM Revision bf9ca1eb (ceph): ceph.spec.in: lttng in SLES12 only
- Over in the SUSE sector, we are trying to enable the SLE_12 and openSUSE_13.2
build targets. The lttng/babeltrace stu... - 10:33 AM Revision c84722a9 (ceph): ceph.spec.in: fix boost-random build dependency for SLE/openSUSE
- In Fedora, RHEL and CentOS there is a package called boost-random.
In SLE/openSUSE, there is no such package.
Signed... - 10:25 AM devops Bug #13375: SLE12 build in OBS: systemd-tmpfiles not found in post-build-scripts
- https://github.com/ceph/ceph/pull/6171
- 10:25 AM devops Bug #13375 (Resolved): SLE12 build in OBS: systemd-tmpfiles not found in post-build-scripts
- ...
- 09:00 AM Revision ccf26850 (ceph): rgw: we should not overide Swift sent content type
- Fixes: #12363
backport: hammer
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
(cherry picked from commit 423cf1... - 09:00 AM Revision 6829ee29 (ceph): rgw: send Content-Length in response for GET on Swift account.
- Fixes: #12158
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
(cherry picked from commit 5f47b11791cd46ce... - 08:32 AM Bug #13374 (Resolved): systemd: no rbdmap systemd unit file
- The init-rbdmap script was not converted to systemd and remains to be the last init script that was not converted to ...
- 01:57 AM Revision d0ecb0ab (ceph): doc/release-notes: initial v9.1.0 notes
- Signed-off-by: Sage Weil <sage@redhat.com>
10/05/2015
- 11:48 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- I have a theory on how to fix the packaging situation with EPEL + Firefly (http://www.spinics.net/lists/ceph-devel/ms...
- 11:48 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- Still see run:
http://pulpito.ceph.com/teuthology-2015-10-05_10:28:07-upgrade:firefly-hammer-x:stress-split-infernal... - 11:35 PM rbd Bug #13371 (Closed): "[ FAILED ] LibRBD.*" tests in upgrade:firefly-hammer-x:stress-split-infer...
- (1st run for firefly-hammer-x/stress-split part of the suite)
Run: http://pulpito.ceph.com/teuthology-2015-10-05_1... - 10:39 PM Bug #13370: ceph-disk: ceph-deploy suite fails with dmcrypt (hammer)
- Another dmcrypt test passes on Ubuntu 14.04 "ceph-deploy/basic/{ceph-deploy-overrides/enable_dmcrypt_diff_journal_dis...
- 10:35 PM Bug #13370: ceph-disk: ceph-deploy suite fails with dmcrypt (hammer)
- ...
- 09:53 PM Bug #13370 (Won't Fix): ceph-disk: ceph-deploy suite fails with dmcrypt (hammer)
- h3. Workaround
Run ceph-disk activate manually.
h3. Rationale for Won't fix
The problem revealed by this su... - 10:36 PM rgw Bug #13240: AssertionError: 31457280 != 30932992: s3tests.functional.test_s3.test_multipart_uploa...
- Found it, full handling reorders ops with need_promote() set.
- 09:35 PM rbd Bug #13325 (In Progress): rbd-replay-prep doesn't handle new IO APIs
- 09:33 PM rgw Bug #13239 (Pending Backport): Seg fault 9.0.3-1845-gf1ead76 : RGWRESTSimpleRequest::forward_requ...
- 09:32 PM Revision 3570ec61 (ceph): Merge pull request #6110 from ceph/wip-13239-infernalis
- rgw: set default value for env->get() call
Reviewed-by: Sage Weil <sage@redhat.com> - 09:17 PM Feature #12754 (In Progress): pg auto repair for EC pool
- 08:13 PM Bug #13061 (Resolved): systemd: daemons restart when package is upgraded
- 08:12 PM Revision 42a2c340 (ceph): Merge pull request #6142 from ceph/wip-13061
- ceph.spec.in: Do not always restart the daemons on upgrades/removal
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 08:09 PM Bug #13262 (Resolved): ./mon/Session.h: 75: FAILED assert(sub_map.empty())
- 08:09 PM Revision e389fe12 (ceph): Merge pull request #6105 from liewegas/wip-13262
- mon: ignore messages from disconnected clients; clean up session checks
Reviewed-by: Joao Eduardo Luis <joao@suse.de> - 07:13 PM Bug #13369: "librados/TestCase.cc:216: Failure" in upgrade:firefly-hammer-x:parallel-infernalis-d...
- Same (or similar) tests are currently failing in firefly-backports: #13300
- 06:05 PM Bug #13369 (Duplicate): "librados/TestCase.cc:216: Failure" in upgrade:firefly-hammer-x:parallel-...
- Run: http://pulpito.ceph.com/teuthology-2015-10-02_13:18:08-upgrade:firefly-hammer-x:parallel-infernalis-distro-basic...
- 06:51 PM Revision 678384a1 (ceph): Merge pull request #6176 from liewegas/wip-13283
- osdc/Objecter: send FULL_TRY and FULL_FORCE ops despite full flag
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:07 PM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- Run: http://pulpito.ceph.com/teuthology-2015-10-02_13:18:08-upgrade:firefly-hammer-x:parallel-infernalis-distro-basic...
- 06:00 PM rbd Bug #13220 (In Progress): rbd-replay-prep: crashes on incorrect trace file
- 05:38 PM rbd Bug #13313 (Fix Under Review): Rare failure of TestLibRBD.ObjectMapConsistentSnap
- *master PR*: https://github.com/ceph/ceph/pull/6177
- 05:19 PM Bug #13283: full-tiering.yaml hang
- Allegedly this is the same issue (per irc chat with Sam)
http://qa-proxy.ceph.com/teuthology/teuthology-2015-10-04... - 04:35 PM Bug #13366 (Duplicate): ceph-deploy: "unable to get 'HEALTH_OK' after waiting 15 minutes" in ceph...
- Run: http://pulpito.ceph.com/teuthology-2015-10-04_01:10:07-ceph-deploy-hammer-distro-basic-vps/
Jobs: ['1088030', '... - 04:09 PM CephFS Bug #13364 (Resolved): LibCephFS locking tests are failing and/or lockdep asserting
- Run: http://qa-proxy.ceph.com/teuthology/teuthology-2015-10-04_05:00:08-smoke-master-distro-basic-multi
Job: 1088065... - 02:27 PM rgw Backport #13360 (In Progress): RGW Swift API: responses for several request types don't contain m...
- 02:20 PM rgw Backport #13360 (Resolved): RGW Swift API: responses for several request types don't contain mand...
- https://github.com/ceph/ceph/pull/5532
- 02:27 PM rgw Backport #13361 (In Progress): RGW Swift API: response for GET on Swift account doesn't contain m...
- 02:24 PM rgw Backport #13361 (Resolved): RGW Swift API: response for GET on Swift account doesn't contain mand...
- https://github.com/ceph/ceph/pull/5532
- 02:27 PM rgw Backport #13362 (In Progress): testGetContentType and testHead failed
- 02:26 PM rgw Backport #13362 (Resolved): testGetContentType and testHead failed
- https://github.com/ceph/ceph/pull/5532
- 02:00 PM Revision 767f1f74 (ceph): rgw: force content-type header for swift account responses without body
- This regression was introduced in commit 4cfeca03ade21861ab70ca759f94eb244c16cb39
Fixes: #11438
Signed-off-by: Orit... - 02:00 PM Revision 9139fbbc (ceph): rgw: force content_type for swift bucket stats request
- Fixes: 12095
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
(cherry picked from commit da259e4da1329e1e448d75c4... - 02:00 PM Revision c9226afd (ceph): rgw: enforce Content-Type in Swift responses.
- Swift sends Content-Type HTTP header even if the response
doesn't contain body. We have this behaviour implemented
un... - 02:00 PM Revision e3da03dd (ceph): rgw: shouldn't return content-type: application/xml if content length is 0
- Fixed: #11091
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
(cherry picked from commit 5cc92bb27cfbaee4af24dc3... - 01:28 PM Revision fe54ef84 (ceph): CMake - fix yasm check
- The yasm check was incorrectly including yasm-build assembler files even
when yasm wasn't present. Fix this, and mak... - 01:28 PM Revision ff6223f8 (ceph): CMake - Fix perftools checks
- Signed-off-by: Daniel Gryniewicz <dang@redhat.com>
- 01:17 PM Revision a6a6923c (ceph): osdc/Objecter: send FULL_TRY and FULL_FORCE ops despite full flag
- If a request has the FULL_TRY or FULL_FORCE flag, send it despite a full
pool or cluster.
Signed-off-by: Sage Weil <... - 01:14 PM Revision e7d08b1b (ceph): test/librados/tier.cc: destroy and recreate cache pool on every test
- Namespaces are not sufficient with the checks for 11493 in the mon.
Signed-off-by: Samuel Just <sjust@redhat.com>
(c... - 01:14 PM Revision d7f53442 (ceph): mon: prevent pool with snapshot state from being used as a tier
- If we add a pool with snap state as a tier the snap state gets clobbered
by OSDMap::Incremental::propogate_snaps_to_t... - 01:09 PM Bug #12746: failed assert ctx.manager.pg_inconsistent(pool, 0) on repair_test.yaml
- /a/sage-2015-10-04_18:40:24-rados-wip-sage-testing---basic-multi/1088634
- 12:39 PM Revision 414e80ad (ceph): Merge pull request #607 from dachary/wip-git-ceph-com-firefly
- git ceph com and newdream hostname changes
Reviewed-by: Nathan Cutler <ncutler@suse.cz> - 12:37 PM Revision 8201f0ec (ceph): mon: allow ping through despite synch/quorum status, with session
- Attach sessions to ping messages, too.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:37 PM Revision a8758268 (ceph): mon: always set up session; move waitlist logic
- Unconditionally attach a Session, so that when we push an op back through
dispatch_op it isn't in a weird broken stat... - 12:37 PM Revision 6cf34a3e (ceph): mon: drop any ops from closed sessions in dispatch_op
- If we've closed the session we shouldn't waste our time on this op.
Fixes: #13262 (we should not add a subscription ... - 12:37 PM Revision 12bbc08f (ceph): mon: all MonOpRequests have an attached Session
- ...except in dispatch, where we initially set it up.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:37 PM Revision 17e55b95 (ceph): mon: clean up _ms_dispatch
- Lots of cruft here.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:37 PM Revision 5008da2a (ceph): mon: drop ops on closed sessions early
- We will throw it out in dispatch_op() anyway. Remove the ancient (~2009)
reuse_caps logic too, which doesn't make an... - 11:36 AM Bug #13359 (Resolved): giant stale requests
- http://pulpito.ceph.com/loic-2015-10-05_01:41:20-upgrade:hammer-hammer-backports---basic-vps/1088492/...
- 09:28 AM Revision e2e1bd9c (ceph): mds: avoid emitting cap warnings before evicting session
- In the case where a client dies, and another client immediately
tries to access a file locked by the dead client, we ... - 09:18 AM Revision 85d21af3 (ceph): git.ceph.com
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit a14a951640f79fd7ed217c423dcc9f453c830556)
Conf... - 09:18 AM Revision 4cdfd9ca (ceph): git.ceph.com
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit f062b171f4ab191986cea525c831573109aba2f9) - 09:16 AM Revision 991845ec (ceph): teuthology: some suites still use http://ceph.newdream.net
- This probably redirects to http://ceph.com but ceph.newdream.net still appears in some places
http://tracker.ceph.co... - 09:01 AM Bug #13300: LibRadosTwoPoolsPP tests failing in firefly-backports
- Following https://github.com/ceph/ceph/pull/5236, the test probably need to be adjusted as well.
- 08:46 AM Bug #13300: LibRadosTwoPoolsPP tests failing in firefly-backports
- 08:20 AM Bug #10097: failed: mon_thrash
- http://pulpito.ceph.com/loic-2015-10-05_01:41:20-upgrade:hammer-hammer-backports---basic-vps/1088479
maybe just a ... - 07:48 AM Revision a4ec1fe7 (ceph): tasks/ceph_fuse.py: virtual machines need flexible mount timeout
- 1) add a wait time before the mount attempt to let the cluster get set up.
By default this should be skipped, but for... - 12:56 AM Revision 2c049897 (ceph): common: add latency perf counter for finisher
- Signed-off-by: Xinze Chi <xinze@xsky.com>
- 12:56 AM Revision 392ca8ba (ceph): filestore: add objectstore finisher name
- we could not get perf couter until add finisher name
Signed-off-by: Xinze Chi <xinze@xsky.com> - 12:05 AM Revision 0c70cd44 (ceph): Merge pull request #605 from dachary/wip-buildpackages-test-hammer
- buildpackages: implicit for OpenStack
- 12:03 AM Revision 46b858e7 (ceph): buildpackages: implicit for OpenStack
- When using the teuthology-openstack command, buildpackages is implicit
and does not need to be included when running ... - 12:02 AM Revision 83e666ae (ceph): Merge pull request #585 from dachary/wip-buildpackages-test
- buildpackages: implicit for OpenStack
10/04/2015
- 11:58 PM Revision e0bba701 (ceph): tasks/radosbench: wait just a bit longer
- A run failed due to thrashing.. missed by about 30s (the osd
eventually sent the last reply but we'd already timed ou... - 11:57 PM Revision a5f260ee (ceph): Merge pull request #596 from ceph/wip-radosbench
- tasks/radosbench: wait just a bit longer
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:31 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. powercycle...
- 11:31 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. upgrade...
- 11:30 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. ceph-deploy...
- 11:30 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. rgw...
- 11:29 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. fs...
- 11:28 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. rados...
- 11:28 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. rbd...
- 11:27 PM Stable releases Tasks #13356: hammer v0.94.6
- ...
- 09:58 PM Revision 00a83937 (ceph): White listed WAR 'failed to encode' fixes #13349
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit 37a881aee191038139b37153a25555fc6b7f8fed) - 09:57 PM Revision 555d42c6 (ceph): Merge pull request #602 from ceph/wip13349
- White listed WAR 'failed to encode' fixes #13349
- 01:33 PM Revision 79385a85 (ceph): Merge pull request #6172 from dachary/wip-13354-hammer
- qa/workunits/cephtool/test.sh: don't assume crash_replay_interval=45
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:00 AM Feature #13358 (New): OSD assert with 'Current_Pending_Sector'
- I have noticed when a scrub is running on an OSD that is backed by a JBOD spinning drive that has a single bad block ...
10/03/2015
- 06:23 PM Revision 8d47d9ce (ceph): Merge pull request #601 from dachary/wip-git-ceph-com
- more hammer git ceph com updates
- 05:37 PM Stable releases Tasks #13356 (Resolved): hammer v0.94.6
- h3. Workflow
* "Preparing the release":http://ceph.com/docs/master/dev/development-workflow/#preparing-a-new-relea... - 05:35 PM Bug #13345 (Fix Under Review): OSD: UninitCondition when printing MOSDOp debug output
- https://github.com/ceph/ceph/pull/6174
- 05:32 PM Revision 8e930e3d (ceph): messages/MOSDOp: avoid uninit/undecoded fields in print()
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:43 PM Bug #13109 (Resolved): msg/async leak, observed on mon
- commit:362b18a532a5077a1418c88f5acbc6e468a45a5a
doesn't look like it was async msgr related after all. - 04:42 PM Revision d1e69762 (ceph): Merge remote-tracking branch 'gh/infernalis'
- 04:40 PM Revision 362b18a5 (ceph): mon: fix msg leak in resend_routed_requests
- MForward takes its own ref so we can drop ours.
Signed-off-by: Sage Weil <sage@redhat.com> - 04:40 PM Revision c9dad52c (ceph): Mon: Fix decoded message leak when this monitor is leader
- Fix #13109
Signed-off-by: Haomai Wang <haomai@xsky.com>
Reviewed-by: Sage Weil <sage@redhat.com> - 04:31 PM Bug #13300: LibRadosTwoPoolsPP tests failing in firefly-backports
- Not unsurprisingly, it's happening in the rados suite, too.
- 03:59 PM devops Bug #13331 (Resolved): ceph.spec.in: SUSE needs different systemd Requires
- 03:58 PM devops Backport #13332 (Rejected): ceph.spec.in: SUSE needs different systemd Requires
- We will not backport systemd to hammer.
- 03:56 PM devops Bug #11610 (Resolved): ceph.spec.in: include SUSE in _with_systemd
- 03:55 PM devops Backport #11732 (Rejected): ceph.spec.in: include SUSE in _with_systemd
- We will not backport ...
- 03:27 PM Revision 37a881ae (ceph): White listed WAR 'failed to encode' fixes #13349
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 03:07 PM Bug #13349 (In Progress): "[WRN] failed to encode map e2314 with expected crc".." in upgrade:hamm...
- Per Sage - white list 'failed to encode'
test passed http://pulpito.ceph.com/teuthology-2015-10-03_08:31:28-upgrad... - 12:50 PM Bug #13283 (Resolved): full-tiering.yaml hang
- 12:50 PM Revision 16554eb4 (ceph): Merge pull request #6139 from liewegas/wip-13283
- librados: add FULL_TRY flag; EDQUOT != ENOSPC
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:47 PM devops Bug #13355 (Fix Under Review): docker-test.sh fails because user root already exists
- 12:46 PM devops Bug #13355 (In Progress): docker-test.sh fails because user root already exists
- https://github.com/ceph/ceph/pull/6173
- 12:32 PM devops Bug #13355 (Resolved): docker-test.sh fails because user root already exists
- I run the command: ...
- 12:45 PM Revision 4698e241 (ceph): tests: allow docker-test.sh to run under root
- Do not attempt to create a user if it is root because it already exists.
http://tracker.ceph.com/issues/13355 Fixes:... - 12:42 PM Revision a1f76ee6 (ceph): tests: remove fedora docker files
- They are not used (missing version number at the end of the directory).
Signed-off-by: Loic Dachary <ldachary@redhat... - 12:30 PM Revision 32281611 (ceph): qa/workunits/cephtool/test.sh: don't assume crash_replay_interval=45
- e.g., it's 5 in teuthology's ceph.conf.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 80b723... - 12:27 PM Backport #13354: tests: do not assume crash_replay_interval 45
- https://github.com/ceph/ceph/commit/80b7237e5e74d12b9d8b1f96ea535c96bdff9c6f is the original commit
- 12:27 PM Backport #13354 (Resolved): tests: do not assume crash_replay_interval 45
- https://github.com/ceph/ceph/pull/6172
- 11:53 AM Revision cb6e7cb0 (ceph): git.ceph.com
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit a14a951640f79fd7ed217c423dcc9f453c830556)
Conf... - 11:46 AM Revision c2f60eb2 (ceph): git.ceph.com
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit f062b171f4ab191986cea525c831573109aba2f9) - 11:43 AM Revision 738667c4 (ceph): teuthology: some suites still use http://ceph.newdream.net
- This probably redirects to http://ceph.com but ceph.newdream.net still appears in some places
http://tracker.ceph.co... - 10:49 AM devops Bug #13353: ceph_selinux manpage is made even when selinux is not being built
- https://github.com/ceph/ceph/pull/6171
https://github.com/SUSE/ceph/commit/f52d751e66d0215749c4f2c464d77b669eb64b9e
- 10:22 AM devops Bug #13353 (Resolved): ceph_selinux manpage is made even when selinux is not being built
- If the ...
- 09:49 AM devops Bug #13324 (In Progress): run-make-check.sh fails on SLE-12 (needs %bcond_with selinux)
- Replaced hack with a proper solution: https://github.com/ceph/ceph/pull/6171
- 09:42 AM devops Bug #13352 (Fix Under Review): RPM: default g++ garbage collection settings need tweaking on some...
- https://github.com/ceph/ceph/pull/6171
- 09:14 AM devops Bug #13352 (In Progress): RPM: default g++ garbage collection settings need tweaking on some mach...
- 09:08 AM devops Bug #13352 (Resolved): RPM: default g++ garbage collection settings need tweaking on some machines
- On machines with 8GB of physical memory in the openSUSE Build Service, attempts to build infernalis are prematurely c...
- 09:41 AM devops Bug #13351 (Fix Under Review): RPM: infernalis does not build in openSUSE Build Service
- https://github.com/ceph/ceph/pull/6171
- 08:53 AM devops Bug #13351 (Resolved): RPM: infernalis does not build in openSUSE Build Service
- Although we are trying to support SUSE builds in ...
- 09:40 AM devops Bug #13346 (Fix Under Review): ceph %post scriptlet assumes existence of user/group created by a ...
- https://github.com/ceph/ceph/pull/6171
- 07:52 AM Revision ad833044 (ceph): rgw:add --reset-regions for regionmap update
- Fixes: #12964
Signed-off-by: Weijun Duan <duanweijun@h3c.com>
(cherry picked from commit 95685c19d6f1eab50b903e61273... - 07:41 AM Bug #13162 (Resolved): update docs to point to download.ceph.com
- 07:40 AM Backport #13169 (Resolved): update docs to point to download.ceph.com
- 07:40 AM Revision 028da252 (ceph): Merge pull request #5993 from SUSE/wip-13169-firefly
- update docs to point to download.ceph.com
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 07:39 AM Backport #13170 (Resolved): update docs to point to download.ceph.com
- 07:39 AM Revision 5b25fc9c (ceph): Merge pull request #6156 from dachary/wip-13170-hammer
- doc: update docs to point to download.ceph.com
Reviewed-by: Abhishek Varshney <abhishek.varshney@flipkart.com> - 02:32 AM Bug #13350: "Error cancelling global ust listener thread" errors
- It would seem that this commit has stopped working for some reason:...
- 02:16 AM Bug #13350: "Error cancelling global ust listener thread" errors
- A quick jab at google indicates that the error might be related to a missing ...
- 01:58 AM Bug #13350: "Error cancelling global ust listener thread" errors
- (Not that I don't want to look at it, but I will have to do some digging/learning and that will take some time.)
- 01:57 AM Bug #13350: "Error cancelling global ust listener thread" errors
- Hi Yuri. This test failure is happening in Ubuntu 14.04, right? My commit cited in the description affects RPM distri...
10/02/2015
- 11:39 PM Bug #13350: "Error cancelling global ust listener thread" errors
- Nathan, can you take a look at this, pls?
- 11:24 PM Bug #13350 (Resolved): "Error cancelling global ust listener thread" errors
- See lots of those, seem benign
Run: http://pulpito.ceph.com/teuthology-2015-10-02_10:48:43-upgrade:hammer-x:point-to... - 11:18 PM Bug #13349 (Resolved): "[WRN] failed to encode map e2314 with expected crc".." in upgrade:hammer-...
- Run: http://pulpito.ceph.com/teuthology-2015-10-02_10:48:43-upgrade:hammer-x:point-to-point-x-infernalis-distro-basic...
- 09:47 PM Revision 3ed25c1f (ceph): librados: document new flag
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:46 PM Bug #13109: msg/async leak, observed on mon
- One more leak in the other path too, pushed a fix to wip-sage-testing.
- 01:43 PM Bug #13109 (Fix Under Review): msg/async leak, observed on mon
- https://github.com/ceph/ceph/pull/6149
- 09:17 PM Revision 79d8f895 (ceph): Merge pull request #6169 from rzarzynski/wip-13326
- rgw: improve handling of already removed buckets in object expirer.
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 09:11 PM CephFS Bug #13334: delayed revoke warning in test_client_recovery test
- Oh, it's even simpler. Can just switch the order of locker->tick and server->find_idle_sessions to get rid of this b...
- 09:04 PM CephFS Bug #13334: delayed revoke warning in test_client_recovery test
- Yeah, this is racy because mds_session_timeout is 60s, and so is the threshold for emitting that warning.
Actually... - 05:59 AM CephFS Bug #13334 (Resolved): delayed revoke warning in test_client_recovery test
- http://pulpito.ceph.com/teuthology-2015-09-29_23:04:01-fs-infernalis---basic-multi/1077881/...
- 08:15 PM devops Bug #13346 (In Progress): ceph %post scriptlet assumes existence of user/group created by a diffe...
- 08:06 PM devops Bug #13346: ceph %post scriptlet assumes existence of user/group created by a different package
- makes sense to me
- 07:56 PM devops Bug #13346 (Resolved): ceph %post scriptlet assumes existence of user/group created by a differen...
- https://github.com/ceph/ceph/commit/ceb93e8e69e125c9358f63b0099e7509b6624bcf moved the creation of the "ceph" user an...
- 08:11 PM Backport #13347 (Resolved): osd/ReplicatedPG.cc: 7247: FAILED assert(agent_state)
- This is present in v0.94.4. Commit: e72bdc3bf1541e445f74def70b5aa185f1757468
- 08:10 PM Bug #13190 (Pending Backport): osd/ReplicatedPG.cc: 7247: FAILED assert(agent_state)
- 07:54 PM Revision 8610de81 (ceph): use simplifed messenger constructor for clients
- This is all mechanical except the calculation of the nonce, which is
now always randomized for clients.
Fixes: #1303... - 07:53 PM Revision 9d059c3f (ceph): msg: add simplified messenger constructor
- Several callers create messengers using exactly the same parameters:
- reading the ms type from cct that is also pas... - 07:39 PM Bug #13345 (Resolved): OSD: UninitCondition when printing MOSDOp debug output
- I think this is a result of the optimized decoding. :(
http://pulpito.ceph.com/ubuntu-2015-10-01_23:29:00-fs-greg-fs... - 07:33 PM devops Backport #13333 (Resolved): ceph.spec.in: SUSE needs different systemd Requires
- 07:26 PM devops Backport #13333 (In Progress): ceph.spec.in: SUSE needs different systemd Requires
- https://github.com/ceph/ceph/pull/6168
- 07:30 PM Revision 3139ab4d (ceph): Merge pull request #6168 from SUSE/wip-13333-infernalis
- ceph.spec.in: correctly declare systemd dependency for SLE/openSUSE
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 07:24 PM Revision 929e5d04 (ceph): ceph.spec.in: correctly declare systemd dependency for SLE/openSUSE
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
(cherry picked from commit 7b1882f87509092380d11ec68b504a7bc1f77830) - 06:54 PM Revision 5f201625 (ceph): Merge pull request #549 from ceph/wip-krbd-fio
- Add rbd fio test to exercise block IO on all format/features
- 06:12 PM Revision 8d8fcee4 (ceph): osd/ReplicatedPG: exempt MDS from the failsafe check, too
- This mimics the prior behavior. We probably want to change this at some
point!
Signed-off-by: Sage Weil <sage@redha... - 05:44 PM Revision ab76f766 (ceph): upgrade/hammer-x/point-to-point: use different client for second rgw
- Can't do 2 rgw's on the same client id.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit a0f019... - 05:41 PM Revision 8e115c97 (ceph): rbd fio tests using rbd engine, tests on clones as well using features ...
- Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
- 05:41 PM Revision b5cf466a (ceph): krbd test using fio for format 2 and features 1 and 2.
- Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
- 05:41 PM Revision 15e890e0 (ceph): krbd fio tests using sync engine for format 2 and features 1 and 2.
- Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
- 05:41 PM Revision 971c5fc2 (ceph): rbd io tests using fio, various fio options can be specified in yaml
- test rbd or krbd using fio, can also run io on rbd clones if option is specified in yaml
various options like image-s... - 05:32 PM Revision 138d2d79 (ceph): Merge pull request #599 from ceph/wip-hammer-x
- upgrade/hammer-x/point-to-point: use different client for second rgw
- 05:27 PM Bug #13275 (Resolved): "Error ENOENT: unrecognized pool"
- I fixed this a couple days ago, should be okay now.... https://github.com/ceph/ceph-qa-suite/commit/0e2814d81e882dbaa...
- 03:13 PM Bug #13275: "Error ENOENT: unrecognized pool"
- Run: http://pulpito.ceph.com/teuthology-2015-10-01_17:10:08-upgrade:hammer-x-infernalis-distro-basic-vps/
Logs: http... - 05:24 PM Revision a0f0194a (ceph): upgrade/hammer-x/point-to-point: use different client for second rgw
- Can't do 2 rgw's on the same client id.
Signed-off-by: Sage Weil <sage@redhat.com> - 04:41 PM Revision 9eb65dd1 (ceph): tasks/cephfs: move mds_scrub_checks
- ...into a CephFSTestCase.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:41 PM Revision 0584b9c8 (ceph): tasks/cephfs: fix test_journal_migration
- It was trying to get the output file from
a different remote than the one used to
run the journal tool.
Signed-off-b... - 04:41 PM Revision 62247f20 (ceph): tasks/cephfs: fix FuseMount bin path in vstart
- FuseMount only uses the prefix for finding the 'ceph'
executable, which is in ./ for either cmake or
authtools, not .... - 04:41 PM Revision f8a4b087 (ceph): tasks/cephfs: add needs_trimming decorator
- For tests to advertise that they need the client
to be able to trim its cache (i.e. currently that
means requiring ru... - 04:41 PM Revision efb62ae1 (ceph): tasks/cephfs: mark some tests as @needs_trimming
- So that we can drop these tests when not running
client as root.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:41 PM Revision 8b846b9f (ceph): tasks/cephfs: add vstart runner script
- This is to allow running CephFSTestCase tests
against a vstart cluster, for much faster turnaround
during development... - 04:41 PM Revision cbb85720 (ceph): tasks/cephfs: updates for cmake environ
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:41 PM Revision 23ae9815 (ceph): tasks/cephfs: add instructions to vstart_runner
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:41 PM Revision 06891416 (ceph): tasks/cephfs: stop if needed binaries are absent
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:41 PM Revision 80a9efb7 (ceph): tasks/cephfs: warn if vstart_runner can't import mods
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:41 PM Revision 4f8adf15 (ceph): tasks/cephfs: raise error on non-string stdins
- Shouldn't be any from the fs tests that get run
Signed-off-by: John Spray <john.spray@redhat.com> - 04:41 PM Revision 20e7d2af (ceph): tasks/cephfs: remove a redundant sudo
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:41 PM Revision 904fd768 (ceph): tasks/cephfs: fix FuseMount._asok_path
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:41 PM Revision 99e3a400 (ceph): tasks/cephfs: add --interactive for vstart runner
- Just like interactive-on-error in teuthology.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:41 PM Revision 176123ca (ceph): tasks/cephfs: extend vstart_runner's ctx&run
- Sufficiently to enable using workunits.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:41 PM Revision 03ea0971 (ceph): tasks/cephfs: move journal migration test
- ...into a CephFSTestCase.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:41 PM Revision bab4c7aa (ceph): tasks/cephfs: add Filesystem.exists
- Use this during test setup to check whether
a filesystem is configured at all, before
trying to tear it down.
Signed... - 04:41 PM Revision 120f9d88 (ceph): tasks/cephfs: use Filesystem.rados instead of direct CLI
- Because it's slicker and because I can wrap it for vstart.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:41 PM Revision 48cf533f (ceph): tasks/cephfs: handle endpoint not connected
- Previously failure to stat mnt dir was interpreted
as being unmounted. For "transport endpoint no connected"
error w... - 04:41 PM Revision 7e6f8d49 (ceph): tasks/cephfs: use stdin/stdout in Filesystem._read_data_xattr
- ...so that it doesn't rely on a temp local file and using
run.Raw(">") in commands.
Signed-off-by: John Spray <john.... - 04:41 PM Revision e51cd6be (ceph): tasks/cephfs: prefix override in FuseMount
- For asok and invokation of ceph CLI.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:41 PM Revision be749f8f (ceph): tasks/cephfs: work around fuse weirdness
- I am seeing a strange thing where it seems like sometimes
a ls of /sys/fs/fuse/connections is returning empty when
co... - 04:41 PM Revision 37d55663 (ceph): tasks/cephfs: fix race in TestStrays
- We weren't waiting for export dir to complete (the asok
just starts the process). This wasn't noticeable when runnin... - 04:41 PM Revision 98da1e0d (ceph): tasks/cephfs: refine TestClientLimits.test_client_oldest_tid
- * Instead of creating files in background, create
them in foreground (simpler).
* Instead of creating max_request*2... - 04:41 PM Revision 6f8a35bb (ceph): tasks/cephfs: make memstore dependency declarative
- ...instead of checking for it procedurally during
TestClusterFull.setUp
Signed-off-by: John Spray <john.spray@redhat... - 04:41 PM Revision 684e0deb (ceph): tasks/cephfs: split up TestClientRecovery
- ...into the part that requires a network-isolated
client and the part that doesn't.
This happens to also be the part... - 04:41 PM Revision 9a1ca94e (ceph): tasks/cephfs: cluster_down before fs rm
- In teuthology this isn't needed because we join the
mds child processes after killing them. In vstart
we're killing ... - 04:41 PM Revision d4ecee82 (ceph): tasks/cephfs: add @long_running decorator
- A means for test cases to mark particular methods
as long running, so that the vstart runner can skip
them when runni... - 04:41 PM Revision 1ed6272d (ceph): tasks/cephfs: mark some tests as @long_running
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:41 PM Revision c0e90aa5 (ceph): tasks/cephfs: make FuseMount.teardown safer
- (don't assume fuse_daemon exists)
Signed-off-by: John Spray <john.spray@redhat.com> - 04:41 PM Revision 7884d5b5 (ceph): tasks/cephfs: use raw_cluster_cmd in Filesystem
- ...instead of manually invoking 'ceph' -- so that
it's easier to override this for vstart.
Signed-off-by: John Spray... - 04:41 PM Revision ad562f4b (ceph): tasks/cephfs: make Filesystem rados command overridable
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:41 PM Revision 99a8a123 (ceph): tasks/cephfs: add Filesystem.delete_all
- So that we can clear down filesysteems created by
someone other than ourselves (like vstart.sh)
Signed-off-by: John ... - 04:41 PM Revision f58c119d (ceph): tasks/cephfs: use raw_cluster_cmd instead of manual "ceph"
- It's less repetitive, and I can override it for use with
vstart.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:41 PM Revision e2f8b48d (ceph): tasks/cephfs: add Filesystem._prefix
- So that my vstart subclass can put ./ before
all the commands.
One could set $PATH, but I like to unambiguously poin... - 04:36 PM devops Fix #5900: Create a Python package for ceph Python bindings
- To summarize progress here: that "wip-5900" branch in GitHub will need to be rebased onto the current master branch. ...
- 04:20 PM Revision 81c23745 (ceph): rgw: improve handling of already removed buckets in object expirer.
- Fixes: #13326
Backport: infernalis
Signed-off-by: Radoslaw Zarzynski <rzarzynski@github.com> - 03:50 PM Revision f19a39ca (ceph): Merge pull request #5907 from dachary/wip-release-notes
- release-notes: draft v0.94.4 release notes
Reviewed-by: Sage Weil <sage@redhat.com> - 03:48 PM Revision 662ad523 (ceph): release-notes: draft v0.94.4 release notes
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 03:47 PM Revision 2228c226 (ceph): tools: ceph-release-notes handle multiple issues
- * handle the case where a single pull request is associated with
multiple pull requests
* encapsulate the quest for... - 03:42 PM rgw Backport #13343 (In Progress): /etc/init.d/radosgw restart does not work correctly
- 03:42 PM rgw Backport #13343 (Resolved): /etc/init.d/radosgw restart does not work correctly
- https://github.com/ceph/ceph/pull/6161
- 03:23 PM rgw Backport #13046 (In Progress): RGW : setting max number of buckets for user via ceph.conf option
- 03:22 PM Revision 7de65e7e (ceph): rgw : setting max number of buckets for users via ceph.conf option
- This patch adds a new option "rgw_user_max_buckets" for setting
max number of buckets for users via ceph.conf.
Fixes... - 03:16 PM rgw Bug #12989 (Duplicate): rgw: init_rados failed leads to repeated delete
- 03:13 PM rgw Backport #13052 (In Progress): rgw: init_rados failed leads to repeated delete
- 03:13 PM Revision 297c04d8 (ceph): rgw: init_rados failed leads to repeated delete
- Fixes: #12978
Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
(cherry picked from commit ab4232baa7bcc86e90746e13... - 03:11 PM rgw Backport #13053 (In Progress): GWWatcher::handle_error -> common/Mutex.cc: 95: FAILED assert(r == 0)
- 03:11 PM Revision 4b0686f1 (ceph): rgw: delete finisher only after finalizing watches
- Fixes: #12208
The watch error path might try to schedule a finisher work, delete finisher
only after watch destructi... - 03:10 PM rgw Bug #12208: GWWatcher::handle_error -> common/Mutex.cc: 95: FAILED assert(r == 0)
- https://github.com/ceph/ceph/pull/5678
- 02:59 PM rgw Backport #13054 (In Progress): rgw: region data still exist in region-map after region-map update
- 02:49 PM rgw Backport #13226 (In Progress): Keystone Fernet tokens break auth
- 02:49 PM Revision 6119b152 (ceph): rgw: be more flexible with iso8601 timestamps
- make parsing 8601 more flexible by not restricting the length of seconds
to 5, this allows timestamp to be specified ... - 02:45 PM rgw Backport #13227: With root as default user, unable to have multiple RGW instances running
- Backported all the changes to src/init-radosgw because they seem to make sense in the hammer context.
- 02:36 PM rgw Backport #13227 (In Progress): With root as default user, unable to have multiple RGW instances r...
- 02:40 PM rgw Backport #13225 (In Progress): init script doesn't start daemon - errors silently
- 02:35 PM Revision 544a98fa (ceph): init-radosgw: unify init-radosgw[.sysv]
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 1c45f512a91ee49e9253ba6fd3857af9bd2ae57a) - 02:35 PM Revision f51ab26d (ceph): rgw: fix radosgw start-up script.
- radosgw init script is unable to start radosgw daemon.
as it is relies on requiretty being disabled.
once init script... - 02:35 PM Revision 607904e8 (ceph): init-radosgw: specify pid file to start-stop-daemon
- This fixes restart when multiple instances are running.
Fixes: #12407
Tested-by: Pavan Rallabhandi <pavan.rallabhand... - 02:35 PM Revision eb001d3a (ceph): rgw: init script waits until the radosgw stops
- Fixes: #11140
Init script waits in stop action until the radowgw daemons stop.
Signed-off-by: Dmitry Yatsushkevich <... - 02:35 PM Revision d00c52b8 (ceph): doc: rgw: fix typo in comments
- Signed-off-by: Nathan Cutler <ncutler@suse.cz>
(cherry picked from commit 05cf0db22dc3a9cb2bf4b86b8f240683c23f41ac) - 02:35 PM Revision 2a733e9e (ceph): init-radosgw: look in /var/lib/ceph/radosgw
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit a4bb992426b39188e750fce9198052ca0d510117) - 02:27 PM rgw Bug #12407: With root as default user, unable to have multiple RGW instances running
- https://github.com/ceph/ceph/pull/6037
- 02:25 PM rgw Backport #13228 (In Progress): rgw: segments are read during HEAD on Swift DLO
- 02:25 PM Revision 9ab9c445 (ceph): rgw: don't read actual data on user manifest HEAD
- Fixes: #12780
We unconditionally read all the data, which is not needed
when doing HEAD operation on user manifest ob... - 02:23 PM rgw Bug #12780: rgw: segments are read during HEAD on Swift DLO
- https://github.com/ceph/ceph/pull/5996
- 02:19 PM devops Backport #13332: ceph.spec.in: SUSE needs different systemd Requires
- clustered with other ceph.spec.in pull requests : https://github.com/ceph/ceph/pull/5790 or https://github.com/ceph/c...
- 02:08 PM Backport #13341 (In Progress): ceph upstart script rbdmap.conf incorrectly processes parameters
- 08:14 AM Backport #13341 (Resolved): ceph upstart script rbdmap.conf incorrectly processes parameters
- https://github.com/ceph/ceph/pull/6159
- 02:08 PM Revision 6e29e904 (ceph): init-rbdmap: fix CMDPARAMS
- Fixes: #13214
Reported-by: Wyllys Ingersoll <wyllys.ingersoll@keepertech.com>
Signed-off-by: Sage Weil <sage@redhat.c... - 02:06 PM Backport #13336 (In Progress): osd: we do not ignore notify from down osds
- 08:06 AM Backport #13336 (Resolved): osd: we do not ignore notify from down osds
- https://github.com/ceph/ceph/pull/6158
- 02:05 PM Revision 9753551f (ceph): OSDMap.h: add has_been_up_since
- Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry picked from commit 4b00350870e3a43aee5fff7982b3785fe1876634) - 02:05 PM Revision 7161a2c9 (ceph): PG: ignore info from down osd
- Fixes: #12990
Backport: firefly, hammer
Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry picked from commit 930d... - 02:00 PM Backport #13040 (In Progress): common/Thread:pthread_attr_destroy(thread_attr) when done with it
- 02:00 PM Revision 9581f9f4 (ceph): Thread.cc: remove malloc/free pair
- There's no need for mallocing pthread_attr_t in Thread::try_create(),
it can be located on stack as it is freed in sa... - 02:00 PM Revision f1271eae (ceph): Common/Thread: pthread_attr_destroy(thread_attr) when done with it
- When a thread attributes object is no longer required, it should be destroyed using the
pthread_attr_destroy() functi... - 01:47 PM Backport #13170 (In Progress): update docs to point to download.ceph.com
- 01:46 PM Revision 9026c4a7 (ceph): doc: remove mention of ceph-extra as a requirement
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
(cherry picked from commit a6f07e9fa3bd5e50a2d8cfa387b44a39d383fa65) - 01:46 PM Revision e9f4aecf (ceph): doc: Added "Hammer" in the list of major releases.
- Fixes: #12771
Signed-off-by: ritz303 <ritz_303@yahoo.com>
(cherry picked from commit 582f0f64455079290ad3b4ae7338b71... - 01:46 PM Revision faccdce7 (ceph): doc: correct links to download.ceph.com
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
(cherry picked from commit 387d7800359154950431d0984c756f43f21dd9b4) - 01:46 PM Revision 45ed24da (ceph): doc: remove ceph-extras
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
(cherry picked from commit c0ef84fd22aac58b6ec8e58eb4f8dffed306d39e) - 01:39 PM Backport #13171 (In Progress): objecter: cancellation bugs
- 01:38 PM Revision 6ff7b02d (ceph): osdc/Objeter: When cancel op, decrease num_unacked/num_uncommitted.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
(cherry picked from commit 064e8585a04edb3d87b38db6bed03e965cfcb359) - 01:38 PM Revision ba36caba (ceph): osdc/Objecter: In _cancel_linger_op, it should make num_unacked/num_com...
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
(cherry picked from commit 36b62710ddef0ffaee25837a92ca1ac9b353ff05) - 01:38 PM Revision 8f76f4c4 (ceph): osdc/Objecter: Don't forget call _op_cancel_map_check when cancel linge...
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
(cherry picked from commit 7cc963b1c6ab37bf33638dc6eca7848d93f7908f) - 01:38 PM Revision f80d237d (ceph): osdc/Objecter: remove the unuseful code.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
(cherry picked from commit 80f10e3e59dadda2dca4eb62c68af972b701b316) - 01:38 PM Revision a17f2a9a (ceph): osdc/Objecter: optimize Objecter::tick.
- Set bool value is better than insert same value into set<>.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
(cher... - 01:37 PM Revision d815e0aa (ceph): osdc/Objecter: For func op_cancel_writes it can directly call op_cancel.
- Becasue we get write-lock of rwlock, so it is safe to call op_cancel
rather than _op_canchel(homeless_session for thi... - 01:37 PM Revision 53316f36 (ceph): Objecter: Take RLocker when call is_active.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
(cherry picked from commit 89f0112e001a2561f9a5cd705898d43c8909501f) - 01:27 PM Backport #13195 (In Progress): should recalc the min_last_epoch_clean when decode PGMap
- 01:27 PM Revision 68492888 (ceph): mon/PGMap: calc min_last_epoch_clean when decode
- Fixes: #13112
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit d0ac68bf1785b330f3202d924c2203ac... - 01:23 PM Backport #13205 (In Progress): ReplicatedBackend: populate recovery_info.size for clone (bug symp...
- 01:22 PM Bug #12828: ReplicatedBackend: populate recovery_info.size for clone (bug symptom is size mismatc...
- https://github.com/ceph/ceph/pull/6013
- 01:19 PM Backport #13210 (Need More Info): tests : Fixed broken Makefiles after integration of lttng into ...
- Could you please add a reference to a test that fails because of this in hammer ? It will help me make sure the backp...
- 01:12 PM Backport #13233 (In Progress): mon: include min_last_epoch_clean as part of PGMap::print_summary ...
- 01:12 PM Feature #13198: mon: include min_last_epoch_clean as part of PGMap::print_summary and PGMap::dump
- https://github.com/ceph/ceph/pull/6056
- 01:11 PM Revision 7d4b303b (ceph): osd: print min_last_epoch_clean along with pg dump
- Fixes: 13198
Signed-off-by: Guang Yang <yguang@yahoo-inc.com>
(cherry picked from commit f5359f2314ce3e76ed446c01889d... - 01:09 PM Backport #13245 (In Progress): client nonce collision due to unshared pid namespaces
- 12:59 PM Revision aed5a6db (ceph): Merge pull request #595 from ceph/wip-quota
- log-whitelist 'reached quota' for librados test.sh
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:48 PM Bug #13260 (Resolved): osd: must preserve RWORDERED when proxying reads
- we shouldn't need to backport this since it only matter if we proxy *both* reads and writes, and hammer does not do w...
- 12:47 PM Revision 08c15821 (ceph): Merge pull request #6096 from liewegas/wip-13260
- osd/ReplicatedPG: preserve (some) flags when proxying reads
Reviewed-by: Samuel Just <sjust@redhat.com> - 12:44 PM Revision 3e30d5df (ceph): tasks/radosbench: wait just a bit longer
- A run failed due to thrashing.. missed by about 30s (the osd
eventually sent the last reply but we'd already timed ou... - 12:39 PM Bug #13206 (Resolved): OSD::do_recovery() local variable "started" shall be explicitly initialize...
- 12:39 PM Revision c0481cf9 (ceph): Merge pull request #6107 from liewegas/wip-13206
- osd: init started to 0
- 12:38 PM Bug #13114 (Pending Backport): LibRadosWatchNotify.WatchNotify2Timeout
- 12:38 PM Revision 4936f591 (ceph): Merge pull request #6136 from liewegas/wip-13114
- osd/librados: fix notify completion race
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:33 PM Revision 7bb1ceb3 (ceph): log-whitelist 'reached quota' for librados test.sh
- A new test verifies that we are stopped by the pool quota (and get
the right error messages or block). See ceph.git
... - 11:42 AM Bug #12990: osd: we do not ignore notify from down osds
- *infernalis PR*: https://github.com/ceph/ceph/pull/6117
- 10:14 AM Bug #12990: osd: we do not ignore notify from down osds
- What is the commit to be backported ?
- 11:23 AM Bug #13200 (Duplicate): mon: does not check for IO errors on every transaction
- 11:14 AM Backport #13288 (In Progress): hammer: stuck recovering, unfound hit set due to removing it while...
- 11:04 AM Bug #13098: OSD crashed when reached pool's max_bytes quota
- https://github.com/ceph/ceph/pull/6052
- 11:02 AM Backport #13337 (In Progress): segfault in agent_work
- 08:08 AM Backport #13337 (Resolved): segfault in agent_work
- https://github.com/ceph/ceph/pull/6146
- 11:01 AM Revision d8ca88dd (ceph): OSDService::agent_entry: don't use PG::operator<< without pg lock
- Fixes: #13199
Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry picked from commit d422f2820d5beee15117e166546a63... - 10:53 AM Bug #13199: segfault in agent_work
- https://github.com/ceph/ceph/pull/6121
- 10:51 AM Backport #13338 (In Progress): filestore: fix peek_queue for OpSequencer
- 08:09 AM Backport #13338 (Resolved): filestore: fix peek_queue for OpSequencer
- https://github.com/ceph/ceph/pull/6145
- 10:50 AM Revision 397042a0 (ceph): filestore: fix peek_queue for OpSequencer
- Fixes: #13209
Signed-off-by: Xinze Chi <xinze@xsky.com>
(cherry picked from commit 5f7b3f5cde779f1300a35a04df2cdb1299... - 10:49 AM Backport #13339 (In Progress): mon: check for store writeablility before participating in election
- 08:10 AM Backport #13339 (Resolved): mon: check for store writeablility before participating in election
- https://github.com/ceph/ceph/pull/6144
- 10:49 AM Revision d4e4d85c (ceph): mon/Elector: do a trivial write on every election cycle
- Currently we already do a small write when the *first* election in
a round happens (to update the election epoch). I... - 10:49 AM Revision 20a4c0c4 (ceph): mon/MonitorDBStore: assert/crash if there is a write error
- Do this globally intead of relying on teh zillion mon callers to
check the error code. There are no cases where we w... - 10:47 AM Backport #13340 (In Progress): small probability sigabrt when setting rados_osd_op_timeout
- 08:12 AM Backport #13340 (Resolved): small probability sigabrt when setting rados_osd_op_timeout
- https://github.com/ceph/ceph/pull/6143
- 10:36 AM Backport #13039 (Need More Info): hammer: osd/PG.cc: 6879: FAILED assert(pg->peer_info.count(so))
- This backport needs https://github.com/ceph/ceph/pull/4784 which has not been backported. I suppose it does not make ...
- 10:24 AM Bug #10794: ceph_test_rados: incorrect buffer at pos ...
- https://github.com/ceph/ceph/pull/4784
- 10:19 AM Revision b9159521 (ceph): ceph.spec.in: Do not always restart the daemons on removal
- There is no need to restart the daemons when removing ceph-selinux
package if SELinux is not enabled.
Fixes: #13061
... - 10:19 AM Revision c95c14ba (ceph): ceph.spec.in: Do not always restart the daemons on upgrades
- This patch minimizes the amount of daemon stop/start procedures when
upgrading ceph-selinux package. With this patch,... - 10:06 AM Bug #12665: osd/ReplicatedPG.cc: 2706: FAILED assert(p != snapset.clones.end())
- Here is a complete log with debug osd = 20 from startup to crash.
https://www.dropbox.com/s/62v6rprsfo2ghdh/crash.... - 08:38 AM Bug #13061 (Fix Under Review): systemd: daemons restart when package is upgraded
- The PR https://github.com/ceph/ceph/pull/6142
- 08:37 AM Bug #7995: osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- Looking through my OSD logs on a Ceph v9.0.3 cluster running on Trusty with the 4.2 kernels I am seeing multiple of t...
- 08:16 AM CephFS Bug #12297 (Resolved): ceph-fuse 0.94.2-1trusty segfaults / aborts
- 08:14 AM Backport #13342 (Resolved): ceph upstart script rbdmap.conf incorrectly processes parameters
- https://github.com/ceph/ceph/pull/6396
- 08:04 AM Backport #13335 (Resolved): hammer: OSD crashed when reached pool's max_bytes quota
- https://github.com/ceph/ceph/pull/6918
- 05:37 AM Revision 6add6ba2 (ceph): Merge pull request #461 from ceph/wip-client-oldest-tid
- cephfs/test_client_limits.py: update test_client_oldest_tid
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 04:59 AM devops Bug #13324 (Resolved): run-make-check.sh fails on SLE-12 (needs %bcond_with selinux)
- 04:56 AM Bug #13281: create does not work on a cache tier whiteout
- *infernalis commit*: https://github.com/ceph/ceph/commit/a965378e3af1e36b1d741dfe7cfd339816366b49
10/01/2015
- 10:34 PM Revision 392c56c1 (ceph): Merge pull request #6137 from SUSE/wip-13324-infernalis
- install-deps.sh: use %bcond_with selinux on SLE/openSUSE
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:21 PM Bug #13281 (Resolved): create does not work on a cache tier whiteout
- 08:49 PM Bug #13281: create does not work on a cache tier whiteout
- Run: http://pulpito.ceph.com/teuthology-2015-10-01_10:58:14-upgrade:hammer-x-infernalis-distro-basic-vps/
Logs: http... - 09:55 PM Revision 4c089ee9 (ceph): Merge remote-tracking branch 'jdurgin/wip-13281' into infernalis
- Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:53 PM Bug #13263 (Duplicate): 0/-1 whiteouts, all/cache-fs-trunc.yaml
- 09:32 PM Bug #13061 (In Progress): systemd: daemons restart when package is upgraded
- @Boris: back to you. Although I don't have the knowledge to do the proposed change, I'll be available if you need a r...
- 04:46 PM Bug #13061: systemd: daemons restart when package is upgraded
- OK, some more info:
(18:40:09) branto: ktdreyer, sage, loicd: I thought about it a bit and I believe it really cou... - 04:35 PM Bug #13061: systemd: daemons restart when package is upgraded
- @Boris, could you please assign the issue back to me when you collected more information regarding the need for a res...
- 03:58 PM Bug #13061: systemd: daemons restart when package is upgraded
- No idea, but you're right, this introduces a behavior change. @branto, how can we avoid this restart?
- 03:44 PM Bug #13061 (Need More Info): systemd: daemons restart when package is upgraded
- @ken, do you know why the restart of the daemon is necessary when selinux is involved ? The initial addition of this ...
- 03:13 PM Bug #13061: systemd: daemons restart when package is upgraded
- The behavior was changed after v9.0.3 by https://github.com/ceph/ceph/pull/5674 when selinux is involved, the daemons...
- 11:03 AM Bug #13061: systemd: daemons restart when package is upgraded
- It turns out to be unrelated to #13000 :-) Running an upgrade suite to repeat the problem. Maybe it only happens with...
- 09:11 PM Revision b20a1ba5 (ceph): ReplicatedPG: consider IGNORE_CACHE for all maybe_handle_cache calls
- Otherwise, we could erroneously promote a snap after not promoting
the missing head for which we have a cached obc an... - 08:05 PM devops Backport #13333 (Resolved): ceph.spec.in: SUSE needs different systemd Requires
- https://github.com/ceph/ceph/pull/6168
- 08:04 PM devops Backport #13332 (Rejected): ceph.spec.in: SUSE needs different systemd Requires
- 08:04 PM devops Bug #13331 (Pending Backport): ceph.spec.in: SUSE needs different systemd Requires
- *master PR:* https://github.com/ceph/ceph/pull/6114
- 08:03 PM devops Bug #13331 (Resolved): ceph.spec.in: SUSE needs different systemd Requires
- The simple ...
- 08:01 PM devops Backport #13330 (Closed): Backport SUSE systemd specfile fixes to infernalis
- nevermind, I'll do it the right way
- 08:00 PM devops Backport #13330 (Closed): Backport SUSE systemd specfile fixes to infernalis
- 07:59 PM RADOS Bug #13329 (New): EUCLEAN (117) from xfs is very bad (should crash just like EIO)
I suggest we add 117 (EUCLEAN) error to EIO and cause an immediate OSD crash based on filestore_fail_eio config var...- 07:57 PM devops Bug #13324 (Fix Under Review): run-make-check.sh fails on SLE-12 (needs %bcond_with selinux)
- https://github.com/ceph/ceph/pull/6137
- 07:03 PM devops Bug #13324 (Resolved): run-make-check.sh fails on SLE-12 (needs %bcond_with selinux)
- When I try to run install-deps.sh from infernalis on SLE-12, it chokes on the selinux-related BuildRequires in the sp...
- 07:50 PM Linux kernel client Bug #13328 (Resolved): fix notify completion race
- See #13114 for the userspace fix. Do the same in the kernel:
- record the notify_id in the notify ack
- ignore w... - 07:47 PM Revision 1df2cc2b (ceph): install-deps.sh: use %bcond_with selinux on SLE/openSUSE
- http://tracker.ceph.com/issues/13324 Fixes: #13324
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 07:44 PM Bug #13109: msg/async leak, observed on mon
- much simpler set of leaks:
/a/sage-2015-10-01_11:19:41-rados:verify-infernalis---basic-multi/1079757
it's MLog ... - 07:38 PM Bug #13283 (Fix Under Review): full-tiering.yaml hang
- https://github.com/ceph/ceph/pull/6139
- 07:37 PM Revision de3c9d59 (ceph): rados/singleton-nomsgr/all/full-tiering: time out rados -p
- We will hit a quota and block (not error out).
See #13283
Signed-off-by: Sage Weil <sage@redhat.com> - 07:36 PM rgw Bug #13326 (Fix Under Review): rgw: objexp collector should specially treat ENOENT on reading buc...
- Pull request: https://github.com/ceph/ceph/pull/6138.
- 07:29 PM rgw Bug #13326 (In Progress): rgw: objexp collector should specially treat ENOENT on reading bucket info
- 07:23 PM rgw Bug #13326 (Resolved): rgw: objexp collector should specially treat ENOENT on reading bucket info
- Currently we signalize an error if the bucket that owns an expired object cannot be found. This behavior is wrong bec...
- 07:34 PM Revision 32962740 (ceph): ceph_test_rados_api_aio: test pool full gets EDQUOT when FULL_TRY flag ...
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:21 PM rbd Bug #13325 (Resolved): rbd-replay-prep doesn't handle new IO APIs
- The new IO API methods which accept fadvise hints are ignored by rbd-replay-prep. Therefore, for example, running 'r...
- 07:13 PM Bug #13323: test.sh: osd/ReplicatedPG.cc: 8851: FAILED assert(head_obc)
- 06:33 PM Bug #13323 (Resolved): test.sh: osd/ReplicatedPG.cc: 8851: FAILED assert(head_obc)
- ubuntu@teuthology:/a/samuelj-2015-09-30_00:41:27-rados-wip-sam-testing-distro-basic-multi/1078220/remote
- 07:03 PM Revision 8b1f2342 (ceph): librados: expose OPERATION_FULL_TRY flag
- Allow librados users to opt to receive ENOSPC or EDQUOT when they submit
an operation against a full cluster. This s... - 07:01 PM Revision ea93ead2 (ceph): osd: return -EDQUOT instead of -ENOSPC if it is a pool quota
- The pool quota error should return EDQUOT intead of ENOSPC.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:53 PM Bug #13114: LibRadosWatchNotify.WatchNotify2Timeout
- https://github.com/ceph/ceph/pull/6136
- 06:53 PM Bug #13114 (Fix Under Review): LibRadosWatchNotify.WatchNotify2Timeout
- 06:50 PM Revision e86d0338 (ceph): osdc/Objecter: distinguish between multiple notify completions
- We may send a notify to the cluster multiple times due to OSDMap
changes. In some cases, earlier notify attempts may... - 06:50 PM Revision 049ea702 (ceph): osd: reply to notify request with our unique notify_id
- The OSD assigns a unique ID to each notify it queues for
processing. Include this in the reply to the notifier so th... - 05:31 PM rbd Bug #13320 (Duplicate): librbd: error cleaning up id object after creation failed: (2) No such f...
- This is #13281
- 04:07 PM rbd Bug #13320 (Duplicate): librbd: error cleaning up id object after creation failed: (2) No such f...
- This is a new fio test that I ran against infernalis, 2 tests have passed but many have failed due to below issue, No...
- 05:31 PM Bug #13322 (Resolved): divergent_priors2: Error ENXIO: problem getting command descriptions from ...
- ubuntu@teuthology:/a/samuelj-2015-09-30_00:41:27-rados-wip-sam-testing-distro-basic-multi/1078084/remote
- 04:34 PM devops Feature #13321: RPM: separate spec file for ceph-common
- Just my $.02: I would not create a separate spec files for client and server, it would probably be easier to introduc...
- 04:26 PM devops Feature #13321 (Rejected): RPM: separate spec file for ceph-common
- Currently ceph-common is built as a subpackage using a single spec-file, together with the server-side packages.
H... - 04:19 PM Revision ed788dc4 (ceph): Merge pull request #594 from dachary/wip-13250-ceph-deploy-branch-hammer
- ceph-deploy: fix ceph-deploy-branch config options
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:51 PM Revision 8a21398f (ceph): Merge remote-tracking branch 'gh/infernalis'
- 03:19 PM Feature #13319: ceph-objectstore-tool: add feature to adjust object_info size
- The tool should also verify that the head object clone_size has the correct value in the event that the object is a c...
- 03:17 PM Feature #13319 (New): ceph-objectstore-tool: add feature to adjust object_info size
- 03:16 PM Bug #13116 (Resolved): osd: pg stuck in replay
- 03:04 PM Revision 965e6289 (ceph): Merge pull request #6114 from SUSE/wip-suse-spec-fixes
- ceph.spec.in: correctly declare systemd dependency for SLE/openSUSE
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 03:03 PM Revision 8d02f49e (ceph): Merge branch 'wip-mdscap'
- Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 03:02 PM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- Run: http://pulpito.ceph.com/teuthology-2015-09-30_13:18:07-upgrade:firefly-hammer-x:parallel-infernalis-distro-basic...
- 02:34 PM devops Bug #13318: install-deps.sh tries to install openSUSE-release even on SLE
- https://github.com/ceph/ceph/pull/6134
- 02:33 PM devops Bug #13318 (Resolved): install-deps.sh tries to install openSUSE-release even on SLE
- On second thought, infernalis is enough.
- 02:32 PM devops Bug #13318 (Pending Backport): install-deps.sh tries to install openSUSE-release even on SLE
- 02:02 PM devops Bug #13318 (Resolved): install-deps.sh tries to install openSUSE-release even on SLE
- In install-deps.sh there is a line:...
- 02:15 PM Revision 99651f0e (ceph): Merge pull request #6134 from SUSE/wip-13318-infernalis
- install-deps.sh: openSUSE-release/sles-release/sled-release are always present
- 02:04 PM Revision 0f9dca45 (ceph): install-deps.sh: openSUSE-release/sles-release/sled-release are always ...
- http://tracker.ceph.com/issues/13318 Fixes: #13318
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 01:42 PM Revision ac031443 (ceph): client: clarify setattr forced sync behavior
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:42 PM Revision b6b9e856 (ceph): ceph_test_libcephfs: remove remaining pool name assumptions
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:42 PM Revision aed5cadd (ceph): mds/SessionMap: fix check_access for stray inodes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:42 PM Revision 75692399 (ceph): qa/workunits: drop bash path tests
- ceph_test_libcephfs ones are better.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:42 PM Revision c77450be (ceph): ceph_test_libcephfs: make foo, path tests use unique paths, users
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:42 PM Revision 371ed4b7 (ceph): mds/SessionMap: fix MAY_CREATE check
- It's about caller_uid/gid.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:42 PM Revision a6fe4ae6 (ceph): ceph_test_libcephfs: add AccessTest.User
- Covers read/write/create.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:42 PM Revision d473732d (ceph): mds/MDSAuthCaps: rename args for is_capable
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:42 PM Revision 614e4cf5 (ceph): mds: fix chown/chgrp check and tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:42 PM Revision 96ee6c9f (ceph): mds/MDSAuthCap: verify the caller_gid is valid
- Verify both the caller uid and gid are a match for the given rule.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:42 PM Revision e54ff357 (ceph): mds: drop MAY_CREATE
- The check is a no-op. We already verify the uid/gid combo is valid and
that the dir is writeable with MAY_WRITE. Th... - 01:42 PM Revision 9b48e24d (ceph): unittest_mds_authcap: improve user tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:42 PM Revision 283be861 (ceph): ceph_test_libcephfs: fix LibCephFS.OpenLayout test
- We can't make assumptions about the name of the data pool.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:42 PM Revision 52724169 (ceph): qa/workunits/fs/test_auth_caps: superceded by ceph_test_libcephfs
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:42 PM Revision 1957aedd (ceph): client: do sync setattr when caller != last cap dirtier
- This way we can still do cap writeback in general when the caller is not
the same as the mount_uid/gid, but we flip t... - 01:42 PM Revision a43f5c75 (ceph): mds/Server: skip auth check on session-less mdr's
- The mds internal requests don't have a session.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:42 PM Revision 269e2de0 (ceph): ceph_test_libcephfs: fix update-after-unlink test
- This needs to be done with a user restricted to a path.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:42 PM Revision d76093bc (ceph): mds/Locker: do not ack from do_cap_update
- Caller (handle_client_caps) already does it if we return
false.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:42 PM Revision fa43c6f2 (ceph): mds/SessionMap: move Session method definitions together
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:41 PM Revision 56bece26 (ceph): fix test_path_caps
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:41 PM Revision c5e9d691 (ceph): unittest_mds_authcaps: fix a few unit tests
- The MAY_CREATE conditoin is simple: the created inode must match the caller
uid and gid.
Signed-off-by: Sage Weil <s... - 01:41 PM Revision 43f50c73 (ceph): add caps_dirty to setattr
- Signed-off-by: Nishtha Rai <nishtha3rai@gmail.com>
- 01:41 PM Revision 4867ef0a (ceph): client: add get_{uid,gid} helpers for consistent uid/gids
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:41 PM Revision 2df9bfb4 (ceph): client: consolidate client_mount_{uid,gid} and client_{user,group}_id o...
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:41 PM Revision 0cb36162 (ceph): client: force setattr to MDS when caller's {uid,gid} are not the specif...
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 01:41 PM Revision 9056a482 (ceph): mds: send cap flush ack even when access check failed.
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 01:41 PM Revision 5ed66258 (ceph): mds/MDSAuthCaps: only verify create git when not AUTH_UID_ANY
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:41 PM Revision 868a8711 (ceph): mds/MDSAuthCaps: whitespace
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:41 PM Revision 7b7e2c20 (ceph): mds/MDSAuthCap: fix creation ownership check
- Check uid too.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:41 PM Revision ddc69bb3 (ceph): client/Client: added client_mount_uid and gid as parameters to getattr ...
- Signed-off-by: Nishtha Rai <nishtha3rai@gmail.com>
- 01:41 PM Revision 073e92aa (ceph): test/libcephfs/access: add Path restriction test
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:41 PM Revision 58a6f7c0 (ceph): test/libcephfs/access: add ReadOnly restriction test
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:41 PM Revision 548e34c8 (ceph): test/libcephfs/access: add update_after_unlink test
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:41 PM Revision 10295e9f (ceph): doc:fix path-based restriction
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:41 PM Revision 785b21c9 (ceph): messages: add caller_{uid,gid} to cap msgs
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 01:41 PM Revision c6ab8de9 (ceph): client: add options to specify caller_{uid,gid} of MClientCaps
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 01:41 PM Revision 74e05c6c (ceph): client: allow specifying default caller_{uid,gid} of MClientRequest
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 01:39 PM Revision f0a418dd (ceph): mds/Server: fix check_access
- Pass through correct mask. Clean up formatting.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:39 PM Revision 35f039e8 (ceph): test/libcephfs/access: expand example test a bit
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision b3fdbb66 (ceph): mds/Server: add chown and chgrp check access to setattr
- 01:39 PM Revision d12a388f (ceph): mds/MDSAuthCaps: add test cases for is_capable
- 01:39 PM Revision 4c896c78 (ceph): add stray_prior_path to store path before rename
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 6cd73066 (ceph): add stray_prior_path for is_stray
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 6f2ac9c9 (ceph): add _check_access for async cap updates
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision d0b5a331 (ceph): move _check_access to SessionMap
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision b70d70b9 (ceph): add check_access in _do_cap_update
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 6a6c0688 (ceph): doc/cephfs: path-based restriction
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision b71a9c41 (ceph): mds: fix Server::check_access
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 01:39 PM Revision aea8a0e1 (ceph): ceph_test_libcephfs: skeleton for access tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision 8d78d5c6 (ceph): client: properly set caller_{uid,gid} of readdir request
- save uid/gid of ll_opendir caller in dir_result_t, use the saved
uid/gid for readdir request.
Signed-off-by: Yan, Zh... - 01:39 PM Revision 991d340a (ceph): add snaps(ls,mk,rm,rename) check_access
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 8a29c4e9 (ceph): add rename check_access
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision ea94bc47 (ceph): add link check_access
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision e33cd74e (ceph): add open check_access
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 17c758b5 (ceph): add stray_prior_path to store path before unlink
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 4f71b113 (ceph): MDSAuthCaps: validate create access
- Signed-off-by: Nishtha Rai <nishtha3rai@gmail.com>
- 01:39 PM Revision 00d74805 (ceph): test_auth_caps: remove grp mount
- Signed-off-by: Nishtha Rai <nishtha3rai@gmail.com>
- 01:39 PM Revision 88d74789 (ceph): test_auth_caps: resolve bug with other bits test case
- 01:39 PM Revision a4d5c3b2 (ceph): test_auth_caps: add mkdir check with mode 557
- 01:39 PM Revision 62b95027 (ceph): Server: add create access check for mknod and symlink
- 01:39 PM Revision be7eb672 (ceph): mds/Server: add create access check for openc
- Signed-off-by: Nishtha Rai <nishtha3rai@gmail.com>
- 01:39 PM Revision 5f5cf95d (ceph): MDSAuthCaps: add world bits check logic
- Signed-off-by: Nishtha Rai <nishtha3rai@gmail.com>
- 01:39 PM Revision 3c4eb6a3 (ceph): test_auth_caps: Added test logic for world bits
- 01:39 PM Revision 4ce4b580 (ceph): test_auth_caps: Move trap and cleanup to the top
- 01:39 PM Revision 807d3693 (ceph): client: behave if we can't getattr parents of mount point
- If our cap locks us into a subdirectory (e.g., /foo), we will fail to
getattr on its parents (e.g., /). This is expe... - 01:39 PM Revision d5ebb027 (ceph): Makefile: include ceph-fuse in base target
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision 72935401 (ceph): mds/MDSAuthCaps: add permissions for user bits
- Signed-off-by: Nishtha Rai <nishtha3rai@gmail.com>
- 01:39 PM Revision 1aaee87d (ceph): test_auth_caps: add test for user bits
- Signed-off-by: Nishtha Rai <nishtha3rai@gmail.com>
- 01:39 PM Revision 5b318aa9 (ceph): MDSAuthCaps: add logic for group bits check
- Signed-off-by: Nishtha Rai <nishtha3rai@gmail.com>
- 01:39 PM Revision 9aa6128e (ceph): mds/Server: clean up check_access a bit
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision 74b140ae (ceph): add readdir check_access
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision fb9c3794 (ceph): add setlayout, setdirlayout, setxattr check_access
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision b07e0155 (ceph): unittest_mds_authcap: test lists of allow grants
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision dc199f4d (ceph): mds/Server.cc: drop leading / from path in is_capable check
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision eef20282 (ceph): functional test of mds cap path restriction
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 74b8f0c7 (ceph): qa/workunits/fs/test_path_caps: tolerate existing directories
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision 5a198867 (ceph): Add mknod check_access
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 7f35ae4c (ceph): add symlink check_access
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 3d2e604e (ceph): add symlink test
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 3b42d576 (ceph): add unlink, rmdir check_access
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 9bc2a015 (ceph): add unlink, rmdir check_access test
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 0bb82105 (ceph): client: pass uid, gid to lookup
- The MDS cares about who is performing lookup, too!
Signed-off-by: Sage Weil <sage@redhat.com> - 01:39 PM Revision e24a9cbf (ceph): mds/MDSAuthCaps: normalize path, drop useless constant.
- Use an empty string for no path--this is more efficient. This generalizes
to losing any leading '/' character.
Sign... - 01:39 PM Revision 51f1028a (ceph): mds: calculate path in check_access()
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 6f60c6d1 (ceph): mds/MDSAuthCaps: add cct for debug context
- signed-off-by: Nishtha Rai <nishtha3rai@gmail.com>
Signed-off-by: Sage Weil <sage@redhat.com> - 01:39 PM Revision 0b557d56 (ceph): mds/MDSAuthCaps: fix allow_all
- Empty path is '', not '/'.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:39 PM Revision 622fe9f1 (ceph): mds/MDSAuthCap: drop leading / in paths
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision 7c1614ab (ceph): mds/MDSAuthCap: fix debug prefix
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision a3758346 (ceph): mds/MDSAuthCaps: debug is_capable
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision 425ff669 (ceph): mds: log to cluster log if mds cap parse fails
- It's an admin error; tell an admin.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:39 PM Revision 6c0ebae6 (ceph): mds: whitespace
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision f5cb4e00 (ceph): mds/MDSAuthCaps: fix parse error message
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision 3e781f2e (ceph): mds: mkdir check_access
- Signed-off-by: Jashan Kamboj <jashank42@gmail.com>
- 01:39 PM Revision 57a1860d (ceph): mds/MDSAuthCaps: whitespace
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision 1d82ec46 (ceph): mds/MDSAuthCaps: parse optional gid list
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision 63c29adb (ceph): mds/MDSAuthCaps: move allows() into MDSCapSpec
- Also, fix this so that 'any' implies that we can read or write.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:39 PM Revision 1b0a82ba (ceph): mds/MDSAuthCap: fix path match
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision d0e4fae9 (ceph): mds/MDSAuthCaps: use bitmask for is_capable()
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision 68621e99 (ceph): mds/MDSAuthCaps: cosmetic
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:39 PM Revision c320bde1 (ceph): mds/MDSAuthCap: fix uid and gid types
- int64_t for uid, so we can do a negative "none" value.
gid_t (uint32_t) for gid.
Signed-off-by: Sage Weil <sage@redh... - 01:39 PM Revision a3f7f5aa (ceph): mds/Server: add check_access() hook
- For now, we are doing a very basic permission check. No callers yet.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:39 PM Revision f8d4d804 (ceph): mds/Server: add a few access checks
- (incomplete coverage!)
Signed-off-by: Sage Weil <sage@redhat.com> - 01:39 PM Revision 65eaf848 (ceph): mds/MDSAuthCaps: pass down inode uid.gid and mode
- We will need this to evaluate the unix permissions.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:21 PM RADOS Bug #13111: replicatedPG:the assert occurs in the fuction ReplicatedPG::on_local_recover.
- this sounds like a side-effect of a async msgr bug, but without a full log it is hard to say.
- 01:20 PM Bug #13285 (Duplicate): mon thrashing: failed to reach quorum size 9 before timeout expired
- 12:34 PM Revision 4c0277f1 (ceph): Merge branch 'wip-add-async-log' of git://github.com/yuyuyu101/ceph int...
- 12:01 PM rgw Documentation #13317 (Resolved): ERROR: invalid flag --lazy-remove
- If I try to use "--lazy-remove" flag from the document :
http://docs.ceph.com/docs/cuttlefish/man/8/radosgw-admin/... - 11:30 AM Bug #13291 (Won't Fix): ceph-disk: --zap-disk does not zap the journal device
- ...
- 09:54 AM Bug #13291: ceph-disk: --zap-disk does not zap the journal device
- Have a pull request here
https://github.com/ceph/ceph/pull/6133 - 08:32 AM Bug #13291: ceph-disk: --zap-disk does not zap the journal device
- I have a fix for this, just checking for the correct pull request
- 11:14 AM CephFS Feature #13316 (Closed): cephfs-data-scan: delete unlinked file objects
- Oh, never mind. I just realised that we never have this case, because during scan_extents we'll always create the 0t...
- 11:09 AM CephFS Feature #13316 (Closed): cephfs-data-scan: delete unlinked file objects
Two types:
1 Non-0th data objects who have no 0th object
2 0th data objects that were not tagged in the latest fo...- 10:03 AM Revision 7db35f2e (ceph): Merge pull request #5951 from guangyy/doc-pool
- doc: update doc for with new pool settings
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-by: Kefu Chai <k... - 07:14 AM Bug #13314 (Resolved): Rados bench verification crashing when there's no objects
- https://github.com/ceph/ceph/pull/5853
When specified pool is empty or doesn't contain valid bench objects, rados ... - 06:55 AM Revision 59bcae28 (ceph): ceph-deploy: fix ceph-deploy-branch config options
- The config paramter of download_ceph_deploy does not have a ceph-deploy
item, therefore the ceph-deploy-branch parame... - 06:50 AM Revision 4c57e31c (ceph): ceph-deploy: always zap disk before creating an osd
- The existing logic is to ceph-deploy osd create --zap-disk which will
zap the data device before preparing it. Howeve... - 06:49 AM Revision 487ccb96 (ceph): Merge pull request #592 from ceph/wip-13000-centos-activate
- ceph-deploy: always zap disk before creating an osd
- 05:35 AM CephFS Support #13267: mds heap stats cause warn message but working
- still waiting for solution.
- 12:21 AM Bug #13000 (Resolved): ceph-disk failure to activate with dmcrypt
- 12:20 AM Bug #13251 (Resolved): mon leaks lots on shutodwn
- 12:14 AM rbd Bug #13313 (Resolved): Rare failure of TestLibRBD.ObjectMapConsistentSnap
- ...
09/30/2015
- 11:45 PM Revision 03b4a795 (ceph): Merge pull request #580 from dachary/wip-13250-ceph-deploy-branch
- ceph-deploy: fix ceph-deploy-branch config options
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:22 PM Bug #13251 (Fix Under Review): mon leaks lots on shutodwn
- https://github.com/ceph/teuthology/pull/644
it passes now! /a/sage-13251/1078478 - 07:27 PM Bug #13251: mon leaks lots on shutodwn
- Pretty sure the problem is the fork() we do in common/SubProcess.cc, used to run crush tests via crushtool.
- 01:06 PM Bug #13251 (In Progress): mon leaks lots on shutodwn
- 12:05 AM Bug #13251: mon leaks lots on shutodwn
- ubuntu@teuthology:/ceph/teuthology-archive/samuelj-2015-09-28_22:02:11-rados-wip-sam-testing-distro-basic-multi/10752...
- 10:21 PM Bug #13000 (Fix Under Review): ceph-disk failure to activate with dmcrypt
- 10:12 PM Bug #13000: ceph-disk failure to activate with dmcrypt
- * https://github.com/ceph/ceph-deploy/pull/365
* https://github.com/ceph/ceph-qa-suite/pull/592... - 05:16 PM Bug #13000: ceph-disk failure to activate with dmcrypt
- http://pulpito.ceph.com/loic-2015-09-30_17:27:30-ceph-deploy-infernalis---basic-vps/1078362/ runs long enough for int...
- 02:40 PM Bug #13000: ceph-disk failure to activate with dmcrypt
- Also happens on Ubuntu (see http://pulpito.ceph.com/loic-2015-09-30_15:58:45-ceph-deploy-infernalis---basic-vps).
... - 01:03 PM Bug #13000: ceph-disk failure to activate with dmcrypt
- ...
- 09:53 PM rbd Bug #13309 (Duplicate): [ FAILED ] TestLibRBD.ListChildrenTiered (CentOS 7)
- This is #13281
- 08:57 PM rbd Bug #13309 (Duplicate): [ FAILED ] TestLibRBD.ListChildrenTiered (CentOS 7)
- It passes on Ubuntu 14.04
http://pulpito.ceph.com/loic-2015-09-30_21:51:20-rbd-infernalis---basic-vps/1078456/
... - 09:52 PM rbd Bug #13310 (Duplicate): librbd: error setting image id: (2) No such file or directory
- This is #13281
- 09:16 PM rbd Bug #13310: librbd: error setting image id: (2) No such file or directory
- Also on Ubuntu 14.04
- 09:10 PM rbd Bug #13310 (Duplicate): librbd: error setting image id: (2) No such file or directory
* "rbd/qemu/{cache/none.yaml cachepool/ec-cache.yaml clusters/fixed-3.yaml fs/btrfs.yaml msgr-failures/few.yaml w...- 09:44 PM Bug #13312 (New): ceph-authtool(8) doesn't mention namespace
- and should
- 09:42 PM CephFS Documentation #13311: explain user permission syntax, details
- object_prefix is not mentioned in this doc at all
- 09:36 PM CephFS Documentation #13311: explain user permission syntax, details
- joshd notes that the ceph-authtool manpage has more explanation; maybe at least a "see also", but perhaps some of the...
- 09:33 PM CephFS Documentation #13311 (Resolved): explain user permission syntax, details
- AFAICT http://docs.ceph.com/docs/master/rados/operations/user-management/ doesn't explain:
# for an OSD, 'class-re... - 09:10 PM Backport #13307 (In Progress): dumpling incrementals do not work properly on hammer and newer
- This backport was done by @athanatos and testing it requires the accompanying ceph-qa-suite branch https://github.com...
- 08:32 PM Backport #13307 (Resolved): dumpling incrementals do not work properly on hammer and newer
- https://github.com/ceph/ceph/pull/6132
- 09:05 PM Revision 3c1f7cbc (ceph): OSDMap: fill in known encode_features where possible
- Otherwise, if we get an incremental from hammer (struct_v = 6) we will
encode the full map as if it were before CEPH_... - 08:43 PM Bug #13234: dumpling incrementals do not work properly on hammer and newer
- Sam, thanks for doing the hammer backport[1] for us. Do you intend to merge it directly into "hammer" from "wip-13234...
- 07:37 PM Bug #13234: dumpling incrementals do not work properly on hammer and newer
- PR that went into *infernalis/master*: https://github.com/ceph/ceph/pull/6122
- 05:49 PM Bug #13234: dumpling incrementals do not work properly on hammer and newer
- The hammer version of the test is the ceph-qa-suite branch ceph/wip-13234-hammer. The hammer version of the fix is t...
- 12:37 PM Bug #13234 (Pending Backport): dumpling incrementals do not work properly on hammer and newer
- 12:02 AM Bug #13234: dumpling incrementals do not work properly on hammer and newer
- See https://github.com/athanatos/ceph/tree/wip-13234
- 07:59 PM Bug #11142: "Exception: ceph-objectstore-tool: import failure" in upgrade:firefly-x-hammer-distro...
- Run: http://pulpito.ceph.com/teuthology-2015-09-29_17:00:08-upgrade:firefly-firefly-distro-basic-vps/
Logs: http://q... - 07:29 PM rbd Bug #13304 (Resolved): "TestLibRBD.Metadata , TestLibRBD.UpdateFeatures" tests failed in upgrade:...
- Run: http://pulpito.ceph.com/teuthology-2015-09-27_23:20:01-upgrade:client-upgrade-infernalis-distro-basic-multi/
Jo... - 07:14 PM Revision b750a160 (ceph): Merge pull request #5853 from branch-predictor/bp-rados-fix-noverify
- common/obj_bencher.cc: fix verification crashing when there's no objects
Reviewed-by: Loic Dachary <ldachary@redhat.... - 07:05 PM Bug #13281 (Fix Under Review): create does not work on a cache tier whiteout
- -*master PR*: https://github.com/ceph/ceph/pull/6118-
- 06:58 PM Revision f467a98a (ceph): tasks/ceph_manager: %d -> %s
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:57 PM Revision 01d48a27 (ceph): ceph-deploy: always zap disk before creating an osd
- The existing logic is to ceph-deploy osd create --zap-disk which will
zap the data device before preparing it. Howeve... - 06:54 PM Bug #13275: "Error ENOENT: unrecognized pool"
- Run: http://pulpito.ceph.com/teuthology-2015-09-27_17:02:01-upgrade:hammer-x-infernalis-distro-basic-multi/
Logs: ht... - 06:44 PM Bug #13284 (Resolved): 11429.yaml failure
- 12:58 PM Bug #13284: 11429.yaml failure
- 12:40 PM Bug #13284: 11429.yaml failure
- 06:42 PM rgw Feature #13303 (Resolved): rgw: support keystone v3
- 06:42 PM Revision 5a450f8e (ceph): rados/singleton-nomsgr/all/11429: blackhole osd.0 to close race
- Blackhole filestore ops so that we ensure it doesn't complete
the pg deletions before the restart function does a cle... - 05:19 PM Bug #13185 (Resolved): osd/ReplicatedPG.cc: 11062: FAILED assert(obc) on hammer -> infernalis upg...
- 05:15 PM Revision a1760b49 (ceph): Merge pull request #6117 from athanatos/wip-12990
- Wip 12990
Reviewed-by: Sage Weil <sage@redhat.com> - 05:15 PM Revision 142cfc1a (ceph): Merge pull request #6120 from athanatos/wip-13185
- Wip 13185
Reviewed-by: Sage Weil <sage@redhat.com> - 04:14 PM rgw Feature #13302 (Fix Under Review): rgw: S3 authentication subsystem should be able to use admin c...
- Pull request: https://github.com/ceph/ceph/pull/6131.
- 04:10 PM rgw Feature #13302 (In Progress): rgw: S3 authentication subsystem should be able to use admin creden...
- 04:09 PM rgw Feature #13302 (Resolved): rgw: S3 authentication subsystem should be able to use admin credentia...
- Currently radosgw may only use _admin token_ for accessing Keystone during authenticating requests made through S3 AP...
- 03:50 PM rgw Bug #10606: civetweb keeps receiving data after client canceled download
- finally got around to upgrading to hammer and not seeing this anymore. Also hammer is awesome so far.
- 03:38 PM Revision 3e487c34 (ceph): Merge pull request #6009 from theanalyst/scripts/orig-issue
- scripts: release_notes can track original issue
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:09 PM Revision 756f809f (ceph): Merge pull request #5211 from 0003ydlom/smc3
- MOSDOp/do_op/handle_op: Simple Messenger optimization
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Greg Far... - 02:53 PM Feature #13301 (Resolved): Request for method to track client versions which have connected to Ce...
- Proposed title of this feature request
Method to track client Ceph versions that have connected to cluster.
... - 02:43 PM Bug #13300: LibRadosTwoPoolsPP tests failing in firefly-backports
- ...
- 02:40 PM Bug #13300: LibRadosTwoPoolsPP tests failing in firefly-backports
- How to reproduce:...
- 02:33 PM Bug #13300: LibRadosTwoPoolsPP tests failing in firefly-backports
- ...
- 02:29 PM Bug #13300: LibRadosTwoPoolsPP tests failing in firefly-backports
- We have backported the fix for #10052, which looks like it could be related, but this particular backport is not yet ...
- 02:28 PM Bug #13300 (Won't Fix): LibRadosTwoPoolsPP tests failing in firefly-backports
- While testing the most recent firefly integration branch, ran into the following test failure:
http://pulpito.ceph... - 02:23 PM rbd Subtask #13292 (Fix Under Review): Mirroring API + rbd CLI updates for pool
- *master PR*: https://github.com/ceph/ceph/pull/6129
- 02:10 PM rbd Subtask #13292 (Resolved): Mirroring API + rbd CLI updates for pool
- ...
- 02:20 PM rbd Subtask #13298 (Resolved): Journal registered client entry should store bufferlist payload
- Replace the current name / description fields with a bufferlist. This will allow librbd (and other clients) to store...
- 02:19 PM Backport #12015 (In Progress): LibRadosTwoPools[EC]PP.PromoteSnap failure
- Ready for integration testing.
- 02:15 PM rbd Subtask #13296 (Resolved): Mirroring API + rbd CLI updates for images
- A new "mirroring enabled" field should be added to the RBD image header. Mirroring should not rely on a feature bit....
- 02:13 PM rbd Feature #13295 (New): Consistency group API + rbd CLI updates
- ...
- 02:13 PM rbd Subtask #13294 (Resolved): Journal repair tools for rbd CLI
- ...
- 02:12 PM rbd Subtask #13293 (Resolved): Journal API + rbd CLI updates
- Need API and tooling to allow retrieving information and current status of RBD journals.
- 01:55 PM Bug #13279: upgrade suite: pool_create failed with error -4 EINTR
- also in run: http://pulpito.ceph.com/teuthology-2015-09-28_13:18:08-upgrade:firefly-hammer-x:parallel-infernalis-dist...
- 01:46 PM Bug #13291 (Won't Fix): ceph-disk: --zap-disk does not zap the journal device
- When running ceph-disk prepare --zap-disk /dev/vdb /dev/vdc, only the data device /dev/vdb is zapped. It is counter i...
- 01:34 PM Revision 963f5e55 (ceph): upgrade/hammer-x/tiering: fix upgrade sequence
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:24 PM Revision a53a80b9 (ceph): tasks/ceph_manager: fix logging on failed pool property
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:18 PM Bug #13283: full-tiering.yaml hang
- Sage Weil wrote:
> Previously a full pool would result in ENOSPC. Now it hangs, just like a full cluster. Not real... - 01:17 PM Bug #13283: full-tiering.yaml hang
- Previously a full pool would result in ENOSPC. Now it hangs, just like a full cluster. Not really sure what we want...
- 12:44 PM Bug #12990 (Pending Backport): osd: we do not ignore notify from down osds
- 12:41 PM Revision 960b16fc (ceph): Merge pull request #6127 from wido/mirror-docs-fixes
- docs: Fix styling of newly added mirror docs
- 12:38 PM Bug #12983 (Resolved): handle_sub_read: Bad hash for 116/b1271c9d:test-rados-api-burnupi34-7183-6...
- 12:36 PM Revision 28c57e55 (ceph): Merge pull request #6122 from athanatos/wip-13234
- OSDMap: fill in known encode_features where possible
Reviewed-by: Sage Weil <sage@redhat.com> - 12:35 PM Revision 415a1862 (ceph): Merge pull request #591 from athanatos/wip-13234
- rados: add test for 13234.yaml
Reviewed-by: Sage Weil <sage@redhat.com> - 12:32 PM Bug #13214 (Pending Backport): ceph upstart script rbdmap.conf incorrectly processes parameters
- 12:31 PM Revision b947acbc (ceph): Merge pull request #6109 from liewegas/wip-13214
- init-rbdmap: fix CMDPARAMS
Reviewed-by: Nathan Cutler <ncutler@suse.com> - 12:29 PM Revision 02113ac4 (ceph): init-rbdmap: fix CMDPARAMS
- Fixes: #13214
Reported-by: Wyllys Ingersoll <wyllys.ingersoll@keepertech.com>
Signed-off-by: Sage Weil <sage@redhat.com> - 12:11 PM Revision 04c09ac6 (ceph): mds: fix SnapServer crash on deleted pool
- Signed-off-by: John Spray <john.spray@redhat.com>
- 11:45 AM Revision 2bb3d4be (ceph): docs: Fix styling of newly added mirror docs
- 08:34 AM Backport #12362: stuck incomplete
- We discussed and verified in #ceph-devel. This fix is available in 0.94.3 release.
- 08:29 AM Backport #12362: stuck incomplete
- <smithfarm> vikhyat: 0.94.4 is not out yet, no
<vikhyat> thanks smithfarm
<abhishekvrshny> smithfarm: the target v... - 08:18 AM Backport #12362: stuck incomplete
- <vikhyat> loicd: if git tag --contains 1063f5275d1031812d564a1bd8ada64bed561026
<vikhyat> v0.94.3
<vikhyat> v0.94.3... - 08:30 AM Revision 0ce74916 (ceph): bugfix: should call md_config_t::remove_observer on shutdown
- Signed-off-by: Ruifeng Yang <yangruifeng.09209@h3c.com>
- 07:59 AM Bug #13289 (Rejected): FileStore::mount No close fsid_fd\basedir_fd\current_fd
- FileStore::mount No close fsid_fd\basedir_fd\current_fd...
- 07:10 AM rgw Feature #11944: rgw: RESTful api for period operations
- https://github.com/ceph/ceph/pull/5924
- 05:39 AM CephFS Support #13055: Problem with disconnect fuse by mds
- thx it works.
- 04:19 AM Revision 4e9f1df5 (ceph): rados: add test for 13234.yaml
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 04:16 AM Backport #13288 (Resolved): hammer: stuck recovering, unfound hit set due to removing it while !a...
- https://github.com/ceph/ceph/pull/7883
- 04:16 AM Backport #13287 (Rejected): stuck recovering, unfound hit set due to removing it while !active
- 04:15 AM Bug #13192: stuck recovering, unfound hit set due to removing it while !active
- https://github.com/ceph/ceph/pull/6119
- 12:33 AM Bug #13192 (Pending Backport): stuck recovering, unfound hit set due to removing it while !active
- 01:09 AM Revision 27d40fda (ceph): Merge branch 'wip-12983' of git://github.com/dzafman/ceph into infernalis
- 12:59 AM rgw Bug #13286 (Resolved): rgw:user email can modify to empty when it has values
- user email can be empty in default
but can't modify to empty when it has value
$radosgw-admin user create --uid=t... - 12:52 AM Bug #13002 (Resolved): Accepter::bind won't work correctly in some exception cases
- 12:48 AM Revision 6b1e4a69 (ceph): cleanup: make the pool setting GET decription point to SET description
- Signed-off-by: Guang Yang yguang@yahoo-inc.com
- 12:48 AM Revision ef59f7c7 (ceph): doc: update doc for with new pool settings
- Signed-off-by: Guang Yang yguang@yahoo-inc.com
- 12:33 AM Bug #13199 (Pending Backport): segfault in agent_work
- 12:32 AM Revision bc627ba8 (ceph): Merge pull request #6119 from athanatos/wip-13192
- Wip 13192
Reviewed-by: Sage Weil <sage@redhat.com> - 12:27 AM Revision 90a4193f (ceph): rados: add test for 13234.yaml
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 12:24 AM Revision b7d35d59 (ceph): Merge pull request #6121 from athanatos/wip-13199
- OSDService::agent_entry: don't use PG::operator<< without pg lock
Reviewed-by: Sage Weil <sage@redhat.com> - 12:23 AM Bug #13176 (Resolved): test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::L...
- 12:21 AM Revision 7af863d3 (ceph): Merge pull request #6113 from dachary/wip-13176-objectstore-tool
- ceph-objectstore-tool: delete ObjectStore::Sequencer after umount
Reviewed-by: David Zafman <dzafman@redhat.com> - 12:19 AM Revision bb55d6c0 (ceph): Merge pull request #6036 from liewegas/wip-13116
- osd: fix replay requeue when pg is activating
Reviewed-by: Samuel Just <sjust@redhat.com> - 12:15 AM Revision 41d59fcc (ceph): Merge remote-tracking branch 'gh/infernalis'
- 12:08 AM Bug #13263: 0/-1 whiteouts, all/cache-fs-trunc.yaml
- ubuntu@teuthology:/ceph/teuthology-archive/samuelj-2015-09-28_22:02:11-rados-wip-sam-testing-distro-basic-multi/10751...
- 12:04 AM Revision a965378e (ceph): ReplicatedPG: clearing a whiteout should create the object
- This was uncovered by 75321943729f1d5dfacb68645e3c5483740d66f8. Since
rbd_create() does a stat, the obc is cached as ... - 12:04 AM Bug #13285 (Duplicate): mon thrashing: failed to reach quorum size 9 before timeout expired
- ubuntu@teuthology:/ceph/teuthology-archive/samuelj-2015-09-28_22:02:11-rados-wip-sam-testing-distro-basic-multi/10752...
09/29/2015
- 11:58 PM Bug #13284 (Resolved): 11429.yaml failure
- failure_reason: 'Command failed on mira061 with status 1: ''sudo TESTDIR=/home/ubuntu/cephtest
bash -c \''sudo gre... - 11:55 PM Bug #13283 (Resolved): full-tiering.yaml hang
- Both pools claim to be full, haven't looked any further.
ubuntu@teuthology:/ceph/teuthology-archive/samuelj-2015-0... - 11:44 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- An ObjectStore::Sequencer provided to an ObjectStore must not be deallocated before umount. The ObjectStore::Sequence...
- 11:43 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- 08:54 PM Bug #13176 (Fix Under Review): test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void ...
- https://github.com/ceph/ceph/pull/6113
- 02:34 PM Bug #13176 (In Progress): test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex...
- 12:48 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- The value of r is -22...
- 12:07 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- When things go as expected, the following happens:...
- 12:05 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- ...
- 11:40 AM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- With ...
- 10:54 PM Revision 47f4a039 (ceph): ceph-objectstore-tool: delete ObjectStore::Sequencer after umount
- An ObjectStore::Sequencer provided to an ObjectStore must not be
deallocated before umount. The ObjectStore::Sequence... - 09:42 PM Revision de29da49 (ceph): Merge pull request #6101 from liewegas/wip-fs
- os/fs: fix do loop
Reviewed-by: Kefu Chai <kchai@redhat.com> - 09:40 PM Revision f20f67e1 (ceph): pybind/cephfs: fix DirEntry helpers
- These were referring to constants incorrectly, would
throw exception if called.
Signed-off-by: John Spray <john.spra... - 09:34 PM Bug #13281 (Resolved): create does not work on a cache tier whiteout
- Run: http://pulpito.ceph.com/teuthology-2015-09-29_05:00:01-smoke-master-distro-basic-multi/
Jobs: 1076143
Logs: ht... - 09:30 PM Bug #13280 (Duplicate): "FAILED assert(head_obc)" in smoke-master-distro-basic
- Run: http://pulpito.ceph.com/teuthology-2015-09-29_05:00:01-smoke-master-distro-basic-multi/
Job: 1076136
Logs: htt... - 09:28 PM Revision 7b1882f8 (ceph): ceph.spec.in: correctly declare systemd dependency for SLE/openSUSE
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 09:13 PM Bug #13279 (Duplicate): upgrade suite: pool_create failed with error -4 EINTR
- Run: http://pulpito.ceph.com/teuthology-2015-09-29_10:41:00-upgrade:firefly-hammer-x:parallel-infernalis-distro-basic...
- 09:05 PM Bug #13275: "Error ENOENT: unrecognized pool"
- Run: http://pulpito.ceph.com/teuthology-2015-09-29_10:41:00-upgrade:firefly-hammer-x:parallel-infernalis-distro-basic...
- 03:13 PM Bug #13275 (Resolved): "Error ENOENT: unrecognized pool"
- Run: http://pulpito.ceph.com/teuthology-2015-09-27_17:10:01-upgrade:hammer-x-infernalis-distro-basic-vps/
Job: 1072... - 08:27 PM Backport #12015: LibRadosTwoPools[EC]PP.PromoteSnap failure
- Got it passing "make check", but there was a lot of guesswork involved so I'm hoping someone can review before we unl...
- 08:14 PM Bug #13278 (Closed): ceph-disk fails with bcache as data disk
- ceph-disk detects bcache[0] devices as full disks and subsequently tries to partition them; however this is not suppo...
- 06:21 PM Bug #13134: old leveldb is slow (firefly->hammer upgrade leads to slow requests)
- Yes I meanwhile, and now it seems fine. So it can be closed I guess.
- 02:49 PM Bug #13134: old leveldb is slow (firefly->hammer upgrade leads to slow requests)
- 2015-09-17 20:42:08.250748 7f631a924700 1 heartbeat_map is_healthy 'OSD::osd_op_tp thread 0x7f6313115700' had timed ...
- 05:43 PM Bug #12665 (Need More Info): osd/ReplicatedPG.cc: 2706: FAILED assert(p != snapset.clones.end())
- Paul Emmerich wrote:
> We are encountering the same issue after trying to delete a snapshot.
> Here is a log file w... - 02:38 PM Bug #12665: osd/ReplicatedPG.cc: 2706: FAILED assert(p != snapset.clones.end())
- 05:25 PM rgw Feature #11945 (In Progress): rgw: radosgw-admin commands to control period - including commit
- 05:23 PM rgw Feature #13102 (Fix Under Review): rgw: multisite: copy-if-newer option for data copy
- 05:22 PM rgw Feature #13100 (In Progress): rgw: multisite: data sync: full data sync
- 05:22 PM rgw Feature #13099 (Fix Under Review): rgw: multisite: data sync - init
- 05:21 PM rgw Feature #11939 (In Progress): rgw: dynamic reconfiguration
- 05:12 PM rgw Feature #13277 (In Progress): rgw: prototype sts implementation
- some amount of support for it in the rgw endpoint
- 04:52 PM Revision 5c7505d2 (ceph): s3tests using ec data pool
- Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
- 03:34 PM Bug #13128: mixed client firefly osd with hammer client - rados api test failure
- I have this yaml in testing mode, I will check with subset of test that make sense for this test and update the hamme...
- 03:29 PM rgw Bug #13240 (New): AssertionError: 31457280 != 30932992: s3tests.functional.test_s3.test_multipart...
- Tested on ceph/wip-12983 and it doesn't fix this issue : http://magna002.ceph.redhat.com/vasu-2015-09-29_10:57:06-rgw...
- 03:19 PM Bug #13276 (Duplicate): *** Caught signal (Segmentation fault) ** in upgrade:hammer-x-infernalis-...
- Run: http://pulpito.ceph.com/teuthology-2015-09-27_17:10:01-upgrade:hammer-x-infernalis-distro-basic-vps/
Job: 10728... - 03:18 PM Revision 3f000421 (ceph): rgw: set default value for env->get() call
- Fixes: #13239
This fixes a regression introduced at commit abe4ec293d08b0314bf5c081ace2456073f3a22c.
The host var is... - 03:09 PM rbd Feature #13274 (Resolved): LTTng-UST should be optionally enabled
- The requirements of LTTng-UST cause issues with SElinux / AppArmor, especially when combined with secured QEMU instan...
- 03:02 PM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- I have cloned https://github.com/ceph/samba.git but it doesn't work with secondary groups
- 01:58 PM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- You mean the development version of SAMBA? Which version?
- 01:42 PM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- secondary groups should work if you use the newest developing code. I'am working on posix ACL supporting.
- 06:58 AM CephFS Bug #13268 (Resolved): Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- Tested with a Windows 7 & 2008 client.
When I'm using the ceph_vfs module in SAMBA it seems secondary groups are n... - 02:57 PM Bug #13057: python-setuptools is missing from debian/control
- Which Operating System (type and version) should I use to reproduce this problem ?
- 02:57 PM Bug #13214 (Fix Under Review): ceph upstart script rbdmap.conf incorrectly processes parameters
- https://github.com/ceph/ceph/pull/6109
- 02:54 PM Bug #13236 (Won't Fix): multiple kill commands lead to data lost when stoping ceph
- 02:54 PM Bug #13208 (Pending Backport): small probability sigabrt when setting rados_osd_op_timeout
- 02:53 PM Backport #12959 (In Progress): udev: add devicemapper to partuuid-workaround
- 02:52 PM Bug #13258: osd Take turns to the down ("FAILED assert(0 == "unexpected error")")
- Can you reproduce that crash with
debug osd = 20
debug filestore = 20
debug ms = 1? - 02:49 PM Bug #12829: buffer::list::write_fd on an empty buffer after seeking past the end of the file does...
- 02:46 PM Bug #13206 (Fix Under Review): OSD::do_recovery() local variable "started" shall be explicitly in...
- https://github.com/ceph/ceph/pull/6107
- 02:46 PM Bug #8752 (Can't reproduce): firefly: scrub/repair stat mismatch
- 02:44 PM Bug #13257 (Rejected): Osd fsid file has been tampered with
- Sep 22 21:31:40 ceph2 ceph[2741]: SG_IO: bad/missing sense data, sb[]: 70 00 05 00 00 00 00 18 00 00 00 00 20 00 00 ...
- 02:44 PM Revision 469d35f2 (ceph): osd: init started to 0
- Fixes: #13206
Signed-off-by: Sage Weil <sage@redhat.com> - 02:43 PM Bug #10057 (Can't reproduce): msgr: skipped message on peer reconnect
- 02:42 PM Bug #12992 (Can't reproduce): fail Messenger/MessengerTest.SyntheticStressTest1/1 (simple)
- 02:41 PM Messengers Bug #13072 (Can't reproduce): osd_ping messages not getting through
- 02:40 PM Bug #13074 (Can't reproduce): tcmalloc segfaults in Pipe::writer() when bufferlist goes out of scope
- 02:37 PM Bug #13234: dumpling incrementals do not work properly on hammer and newer
- 02:35 PM Bug #12748 (Fix Under Review): bug with cache/tiering and snapshot reads [merged, needs a test in...
- -https://github.com/ceph/ceph/pull/6106-
- 02:32 PM Bug #12983: handle_sub_read: Bad hash for 116/b1271c9d:test-rados-api-burnupi34-7183-66/foo/head
- 02:17 PM CephFS Bug #13271: Missing dentry in cache when doing readdirs under cache pressure (?????s in ls-l)
- I think this is 62dd63761701a7e0f7ce39f4071dcabc19bb1cf4, which doesn't appear to be in a release yet. See #12297.
... - 02:02 PM CephFS Bug #13271 (New): Missing dentry in cache when doing readdirs under cache pressure (?????s in ls-l)
- The original reporter confirmed that he saw this with 0.94
- 01:22 PM CephFS Bug #13271: Missing dentry in cache when doing readdirs under cache pressure (?????s in ls-l)
- it's fixed by a5984ba34cb684dae623df22e338f350c8765ba5. updating v0.87.1 should fix this problem
- 01:09 PM CephFS Bug #13271 (Closed): Missing dentry in cache when doing readdirs under cache pressure (?????s in ...
- above circumstance does not suppose to happen. because dirp->buffer holds references to inodes.
I found it's bug i... - 10:53 AM CephFS Bug #13271 (Resolved): Missing dentry in cache when doing readdirs under cache pressure (?????s i...
Fuse sends us a series of readdirs, because it only accepts so many entries in each. We only do an MDS request on ...- 01:52 PM Revision bba3ab36 (ceph): mon: combine _ms_dispatch and dispatch
- _ms_dispatch() is the only caller, and it is confusing to have both
dispatch() and dispatch_op() that take the same a... - 01:45 PM Revision 79401c0a (ceph): Merge pull request #588 from ceph/wip-12573
- Removed cuttlefish from configurations as unsupported
- 01:41 PM Revision 7a9a01bf (ceph): Removed cuttlefish from configurations as unsupported
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 01:16 PM Revision 971eb3f6 (ceph): ceph_test_rados_api_tier: fix cleanup of whiteouts
- Doing a normal DELETE on a whiteout returns ENOENT. Use the IGNORE_CACHE
flag to make sure it removes the whiteout, ... - 01:10 PM Revision b134a629 (ceph): osd/ReplicatedPG: allow whiteout deletion with IGNORE_CACHE flag
- If the client specifies IGNORE_CACHE, allow a regular DELETE to zap a
whiteout. Expand test case to verify this work... - 12:52 PM Bug #13262 (Fix Under Review): ./mon/Session.h: 75: FAILED assert(sub_map.empty())
- https://github.com/ceph/ceph/pull/6105
- 12:34 PM Bug #13266 (Resolved): 6.9 shard 1 missing b4e46c09/benchmark_data_plana09_25588_object1430/head/...
- 10:57 AM Revision 8322a5c2 (ceph): Merge pull request #6103 from SUSE/wip-re-redrop-fdupes
- ceph.spec.in: re-re-drop fdupes
Reviewed-by: Boris Ranto <branto@redhat.com> - 10:54 AM CephFS Feature #13272 (New): Run fuse client workloads under cache pressure
We should run at least some workloads in situations where we set client_cache_size to something fairly low, so that...- 09:08 AM Revision a5a361e8 (ceph): Merge pull request #586 from ceph/wip-mdscap
- tasks/cephfs: mds allow
Reviewed-by: John Spray <john.spray@redhat.com> - 07:12 AM Revision 612480b3 (ceph): test/test_rados_tool.sh: implement regression test for bench verify crash
- Truncate all objects after format test, then check whether rados bench rand/seq
still works, or just crashes.
Signed... - 07:11 AM Revision 0c8faf7c (ceph): common/obj_bencher.cc: fix verification crashing when there's no objects
- When specified pool is empty or doesn't contain valid bench objects, rados
can crash because it attempts to memcmp th... - 06:57 AM Revision e42c9aae (ceph): ceph.spec.in: re-re-drop fdupes
- The %fdupes call was dropped by 53072b9019caf72e0313b2804ea174237ed7da33
Later, it got accidentally reinstated by ceb... - 06:44 AM CephFS Support #13267 (Closed): mds heap stats cause warn message but working
- when im using command ceph mds.node2(or any of mds nodes) heap stats - i see output of memory usage,but in a log file...
- 05:25 AM CephFS Bug #11783: protocol: flushing caps on MDS restart can go bad
- I guess I should note that I only saw this the once and it also included a (slightly outdated) version of the vstart ...
- 05:16 AM CephFS Bug #11783: protocol: flushing caps on MDS restart can go bad
- I merged this by checking that it's working manually, but the testing isn't behaving properly so I haven't merged tha...
- 05:21 AM CephFS Bug #13167 (Resolved): mds: replay gets stuck (on out-of-order journal replies?)
- 05:21 AM Revision a467db1d (ceph): Merge pull request #6025 from ukernel/wip-13167
- journaler: detect unexpected holes in journal objects
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 05:19 AM Revision 79cbfc86 (ceph): Merge pull request #575 from ceph/wip-32bits-ceph-fuse
- suites/fs: test ceph-fuse with 32-bits ino_t
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 05:19 AM Revision 119336fb (ceph): Merge pull request #5849 from ukernel/wip-32bits-ceph-fuse
- Wip 32bits ceph fuse
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 05:14 AM Revision e171984b (ceph): Merge pull request #4791 from ceph/wip-11783
- cephfs: detect completed cap flushes
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:12 AM Revision ae62a9cf (ceph): Merge pull request #6070 from jcsp/wip-reformat-subtreemaptest
- Fix reformatting journals containing SUBTREEMAP_TEST events
- 02:02 AM Revision 95cc1549 (ceph): Merge pull request #6082 from jcsp/wip-client-quota-roots
- Fix quota enforcement on subdir mounts
- 01:31 AM Revision 566c8728 (ceph): os/fs: fix aio submit method
- continue in a do while(false) will always eval false and break
out. To repeat, we need while (true) and an explicit ...
09/28/2015
- 11:20 PM Bug #13266: 6.9 shard 1 missing b4e46c09/benchmark_data_plana09_25588_object1430/head//6" in cl...
- Nevermind, sage already fixed this one.
- 11:11 PM Bug #13266 (Resolved): 6.9 shard 1 missing b4e46c09/benchmark_data_plana09_25588_object1430/head/...
- ubuntu@teuthology:/a/samuelj-2015-09-25_22:44:57-rados-wip-sam-testing-distro-basic-multi/1070057/remote
Replica s... - 08:46 PM Revision f133725b (ceph): buildpackages: implicit for OpenStack
- When using the teuthology-openstack command, buildpackages is implicit
and does not need to be included when running ... - 08:42 PM Revision 04f9ae57 (ceph): Merge pull request #6078 from H3C/wip-13208
- Objecter: maybe access wild pointer(op) in _op_submit_with_budget.
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:41 PM Revision 14a36a20 (ceph): Merge pull request #6064 from H3C/wip-rbd-bugfix1
- Objecter: misc fix for segmentation fault.
Reviewed-by: Sage Weil <sage@redhat.com> - 08:40 PM Revision 8d97771c (ceph): Merge pull request #6084 from liewegas/wip-revert-scrub
- Revert "osd: new pool settings: scrub intervals"
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 08:23 PM Revision 424fc1cc (ceph): rgw: set default value for env->get() call
- Fixes: #13239
This fixes a regression introduced at commit abe4ec293d08b0314bf5c081ace2456073f3a22c.
The host var is... - 07:09 PM Revision d73ca4f5 (ceph): Merge pull request #5832 from SUSE/wip-drop-dup-rcceph
- ceph.spec.in: refrain from duplicating %{_sbindir}/rcceph
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 06:33 PM Revision d7b620f9 (ceph): ECBackend::handle_recovery_read_complete: do not expose the hash_info w...
- Aside from expose an ECBackend internal detail, it causes ReplicatedPG
to cache the value causing trouble with WRITEF... - 06:33 PM Revision 892800b4 (ceph): ECBackend::handle_sub_read: restructure hash check and fix part of 12983
- The previous code erroneously assumed that the reads on a single object
would always be in order, and not overlap.
P... - 06:03 PM rgw Bug #13240 (Need More Info): AssertionError: 31457280 != 30932992: s3tests.functional.test_s3.tes...
- (Reassign back to me when it's back in my court!)
- 06:02 PM rgw Bug #13240: AssertionError: 31457280 != 30932992: s3tests.functional.test_s3.test_multipart_uploa...
- Ugh, won't let me link issues across projects. I think this is probably the same bug as http://tracker.ceph.com/issu...
- 05:29 PM Bug #13263: 0/-1 whiteouts, all/cache-fs-trunc.yaml
- Adding debugging to nail this one in tonights tests.
- 05:24 PM Bug #13263 (Duplicate): 0/-1 whiteouts, all/cache-fs-trunc.yaml
- ubuntu@teuthology:/a/samuelj-2015-09-25_22:44:57-rados-wip-sam-testing-distro-basic-multi/1070097/remote
wip-sam-t... - 05:22 PM Bug #12983: handle_sub_read: Bad hash for 116/b1271c9d:test-rados-api-burnupi34-7183-66/foo/head
- /var/lib/teuthworker/archive/sage-2015-09-28_08:14:59-rados-wip-sage-testing---basic-multi/1073896
another build t... - 05:17 PM Revision 405eef2f (ceph): Merge pull request #6098 from liewegas/wip-crash-replay-interval
- don't assume crash_replay_itnerval == 45
Reviewed-by: Samuel Just <sjust@redhat.com> - 05:13 PM Revision 80b7237e (ceph): qa/workunits/cephtool/test.sh: don't assume crash_replay_interval=45
- e.g., it's 5 in teuthology's ceph.conf.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:10 PM Revision 8cf3d15d (ceph): rados/singleton-nomsgr/all/11429: grep osd.0 only
- Restart can be slow enough that osd.1 and 2 finish deleting the
pgs. Verifying one osd sees the instance is sufficie... - 05:02 PM Bug #13262 (Resolved): ./mon/Session.h: 75: FAILED assert(sub_map.empty())
- 2015-09-26T04:27:17.863 INFO:tasks.rados.rados.0.burnupi50.stdout:2556: expect (ObjNum 835 snap 240 seq_num 835)
20... - 04:38 PM Revision a4f9bdbe (ceph): tasks/cephfs: mds allow
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:11 PM rgw Bug #12963 (Fix Under Review): rgw:objects can not be displayed which object name does not contai...
- https://github.com/ceph/ceph/pull/5738
- 03:44 PM Revision 4ef8a0e1 (ceph): Merge pull request #6076 from liewegas/wip-scrub-fix
- osd/PG: compensate for sloppy hobject scrub bounds from hammer
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:31 PM rgw Bug #13261 (Rejected): Object ACLs are not preserved on PUT
- 03:30 PM rgw Bug #13261: Object ACLs are not preserved on PUT
- object ACLs are not supposed to be preserved on overwrite
- 03:03 PM rgw Bug #13261: Object ACLs are not preserved on PUT
- On second thought, this seems to be functioning as designed. Please close/delete.
- 02:42 PM rgw Bug #13261 (Rejected): Object ACLs are not preserved on PUT
- When an object in Ceph is updated, its ACL is reset to private.
To reproduce:... - 03:13 PM Bug #13114: LibRadosWatchNotify.WatchNotify2Timeout
- not able to reproduce locally. reassigning me from this ticket at this moment.
- 02:32 PM rbd Backport #13045 (Fix Under Review): rbd export-diff crashes in librbd::simple_diff_cb
- 02:13 PM rbd Backport #13045 (In Progress): rbd export-diff crashes in librbd::simple_diff_cb
- 02:32 PM Revision 9eea6ea6 (ceph): Merge remote-tracking branch 'gh/wip-infernalis'
- 02:30 PM Bug #13260 (Resolved): osd: must preserve RWORDERED when proxying reads
- if we proxy a write followed by a (rwordered) read, currently the read will return first because the rwordered flag i...
- 02:28 PM Revision c5a9275c (ceph): osd/ReplicatedPG: preserve (some) flags when proxying reads
- In particular, proxy RWORDERED as clients in the real world set
that.
Fixes: #13260
Signed-off-by: Sage Weil <sage@r... - 02:28 PM Revision 93c523c6 (ceph): librbd: diff_iterate needs to handle holes in parent images
- If a clone's parent image snapshot includes a discarded extent,
this was previously causing an assert failure. Inste... - 02:26 PM Revision 359b6844 (ceph): tests: new test case for librbd diff_iterate over discard extents
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit d5650c9cf85188efa73b279c8f4e4723fa4753... - 01:33 PM CephFS Bug #13256 (Fix Under Review): I/O error with cephfs accessing root .snap directory on v9.0.3
- https://github.com/ceph/ceph/pull/6095
- 01:26 PM Revision 994ec60e (ceph): mds: respect max_entries/max_bytes of lssnap request
- Fixes: #13256
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 01:21 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- The Mutex::Lock called from *FileStore::_journaled_ahead* is inlined from ondisk_finisher *Finisher::queue*. There se...
- 12:07 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- The Mutex::Lock called from *FileStore::_journaled_ahead* is inlined from *OpSequencer::dequeue_journal*. There seems...
- 11:21 AM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- Running ceph_objectstore_tool.py in a loop does not reproduce the problem. However...
- 11:02 AM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/8067/console
- 11:52 AM CephFS Feature #13259 (New): Option to disable always writing backtraces to the default data pool
- Currently, this is how we deal with hardlinks vs. layouts specifying non-default data pools: files in the non-default...
- 08:54 AM Revision afcfb050 (ceph): handle_op/do_op: Moving couple of checks from dispatcher to parallelize...
- Signed-off-by: Jacek J. Lakis <jacek.lakis@intel.com>
- 08:54 AM Revision 818d790f (ceph): MOSDOp::decode : Splitting message decoding, new version
- Signed-off-by: Jacek J. Lakis <jacek.lakis@intel.com>
- 07:29 AM Fix #9371: ceph should fail when an argument is of the wrong type
- The way ceph uses positional arguments here is quite creative indeed. It seems also badly documented, e.g. only after...
- 06:27 AM devops Bug #9407 (New): sysvinit: "-a" option and "osd crush update on start" don't work together
- Apparently, the --allhosts option is widely used, so dropping it from init-ceph is not an option.
- 05:56 AM Bug #13258 (Can't reproduce): osd Take turns to the down ("FAILED assert(0 == "unexpected error")")
- -2> 2015-09-28 12:28:28.010597 7f577fbae700 -1 osd.4 pg_epoch: 389 pg[3.f( v 239'35446 (200'32446,239'35446] local-l...
- 03:18 AM Bug #13257: Osd fsid file has been tampered with
- Correction:osd.60 no start success
- 03:16 AM Bug #13257: Osd fsid file has been tampered with
- huanwen ren wrote:
> We have a ceph242 nodes, found the nodes in the start-up process of osd.60 no start success
... - 03:14 AM Bug #13257 (Rejected): Osd fsid file has been tampered with
- We have a ceph242 nodes, found the nodes in the start-up process of osd. Success in 60 has been started.
Through the... - 01:19 AM Bug #13219 (Need More Info): get_device_by_uuid->blkid_find_dev_with_tag() may hang for 3 min
- 12:05 AM Revision b4b66790 (ceph): Merge pull request #582 from ceph/wip-buildpackages-hammer
- hammer backport: buildpackages task
- 12:03 AM Revision 56e95a0e (ceph): Merge pull request #583 from dachary/wip-buildpackages-flock
- buildpackages: flock must --close
- 12:01 AM Revision 0b130d7f (ceph): Merge pull request #584 from dachary/wip-buildpackages-centos-6
- buildpackages: user-data must be per os-type/os-version
09/27/2015
- 09:57 PM Bug #9738 (New): rados cli: objects not present in a snapshot are listed anyway
- 09:54 PM devops Bug #9407 (Fix Under Review): sysvinit: "-a" option and "osd crush update on start" don't work to...
- 09:54 PM devops Bug #9407 (In Progress): sysvinit: "-a" option and "osd crush update on start" don't work together
- -https://github.com/ceph/ceph/pull/6089-
- 09:53 PM Revision 1c8fe7d1 (ceph): buildpackages: user-data must be per os-type/os-version
- CentOS 6.5 needs to install a package and reboot to grow the root file
system. Instead of assuming a common user-data... - 09:42 PM Revision 05228e1e (ceph): buildpackages: user-data must be per os-type/os-version
- CentOS 6.5 needs to install a package and reboot to grow the root file
system. Instead of assuming a common user-data... - 09:41 PM Revision 6d396a32 (ceph): mon/Elector: do a trivial write on every election cycle
- Currently we already do a small write when the *first* election in
a round happens (to update the election epoch). I... - 08:44 PM Backport #13252 (In Progress): mon: does not check for IO errors on every transaction
- 08:43 PM Revision d2bfa190 (ceph): mon/MonitorDBStore: assert/crash if there is a write error
- Do this globally intead of relying on teh zillion mon callers to
check the error code. There are no cases where we w... - 08:17 PM Feature #13142: osd: warning if pg has not been scrubbed for a long time
- I can have a look
- 08:13 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/8054/consoleFull
- 08:01 PM Cleanup #9756 (In Progress): Issues found by Clang
- https://github.com/ceph/ceph/pull/6090 attempts to fix the *-Wtautological-constant-out-of-range-compare*
- 07:20 PM devops Cleanup #3015 (In Progress): order of arguments should not matter for init-ceph
- https://github.com/ceph/ceph/pull/6089
- 04:42 PM devops Cleanup #3015: order of arguments should not matter for init-ceph
- This could be achieved with *getopt*.
- 04:05 PM Cleanup #1042: need const iterator for bufferlist
- "no longer valid?":https://github.com/ceph/ceph/blob/master/src/include/buffer.h#L320
- 12:30 PM Revision e72bdc3b (ceph): osd/ReplicatedPG: tolerate promotion completion with stopped agent
- We may start a promotion, then get a pool update that disables the
agent, and then complete it. We should not segfau... - 12:24 PM Revision d58a0b00 (ceph): add cache tiering test for hammer-x
- Signed-off-by: Kefu Chai <tchaikov@gmail.com>
- 01:11 AM Revision 8941a8b8 (ceph): rados/singleton-nomsgr/all/11439: fix greps
- Signed-off-by: Sage Weil <sage@redhat.com>
09/26/2015
- 11:09 PM Stable releases Tasks #11644: firefly v0.80.11
- h3. ceph-deploy...
- 11:04 PM Stable releases Tasks #11644: firefly v0.80.11
- h3. upgrade...
- 11:03 PM Stable releases Tasks #11644: firefly v0.80.11
- h3. powercycle...
- 11:02 PM Stable releases Tasks #11644: firefly v0.80.11
- h3. rbd...
- 11:01 PM Stable releases Tasks #11644: firefly v0.80.11
- h3. fs...
- 11:00 PM Stable releases Tasks #11644: firefly v0.80.11
- h3. rgw...
- 10:57 PM Stable releases Tasks #11644: firefly v0.80.11
- h3. rados...
- 07:34 PM Stable releases Tasks #11644: firefly v0.80.11
- ...
- 07:31 PM Revision c85d0638 (ceph): use simplifed messenger constructor for clients
- This is all mechanical except the calculation of the nonce, which is
now always randomized for clients.
Fixes: #1303... - 07:27 PM Revision ef24b4ec (ceph): librados: use Messenger factory method
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 5a860bec48348ed4c09256ccd394b33ace6b4f52) - 06:56 PM Revision 3a52acde (ceph): mon/MonClient: use generic Messenger factory
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit e55cb1f68ae1a04cc5d281bea57ee79ef4a8af38) - 05:07 PM CephFS Bug #13256 (Resolved): I/O error with cephfs accessing root .snap directory on v9.0.3
- I am running a test Ceph cluster using Ceph v9.0.3 with all Kernels at 4.2.0 on Ubuntu Trusty. I have enabled snapsho...
- 03:46 PM Revision 8147e68e (ceph): buildpackages: flock must --close
- The process run by flock must not inherit the file descriptor because
this will cause the lock to be held forever sho... - 02:12 PM Backport #13244 (In Progress): client nonce collision due to unshared pid namespaces
- 02:12 PM Revision 83e10f7e (ceph): Merge pull request #6086 from stiopaa1/librados_missingsemicolon
- examples/librados/hello_world.cc:missing semicolon
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 02:04 PM Revision de8da652 (ceph): msg: add simplified messenger constructor
- Several callers create messengers using exactly the same parameters:
- reading the ms type from cct that is also pas... - 01:45 PM Revision 2fea3a56 (ceph): examples/librados/hello_world.cc:missing semicolon
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 01:42 PM rgw Backport #11873: Bucket header is enclosed by quotes
- What happened here? The original backport PR https://github.com/ceph/ceph/pull/4861 was replaced by https://github.co...
- 01:41 PM rgw Backport #11873 (In Progress): Bucket header is enclosed by quotes
- 01:28 PM rgw Backport #12041 (Rejected): DragonDisk fails to create directories via S3: MissingContentLength
- Agreed with original PR author and yehudasa to leave this fix out of firefly.
- 01:23 PM Revision 204e27fe (ceph): buildpackages: flock must --close
- The process run by flock must not inherit the file descriptor because
this will cause the lock to be held forever sho... - 01:21 PM Backport #13255 (Resolved): Increase globalid default for firefly (improves mon responsiveness)
- https://github.com/ceph/ceph/pull/6010
- 12:09 PM Revision c7da300a (ceph): buildpackages: build ceph packages and upload them
- Build Ceph packages from source for the required revision, os_type,
os_version and architecture and upload them to th... - 12:09 PM Revision deb234d7 (ceph): buildpackages: build ceph packages and upload them
- Import install from task.
http://tracker.ceph.com/issues/13031 Fixes: #13031
Signed-off-by: Loic Dachary <loic@dach... - 12:09 PM Revision 04007274 (ceph): buildpackages: pep8 compliance
- http://tracker.ceph.com/issues/13031 Fixes: #13031
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked fro... - 12:09 PM Revision 66bff436 (ceph): buildpackages: re-use config from install task
- So that the packages built match what the install task expects.
http://tracker.ceph.com/issues/13031 Fixes: #13031
... - 12:09 PM Revision 39a0de3c (ceph): buildpackages: build the repository and the packages
- http://tracker.ceph.com/issues/13031 Fixes: #13031
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked fro... - 12:09 PM Revision 82a71bb9 (ceph): buildpackages: make rpm packages
- Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 7e3a271a89d4e7794a1ee547a3105a871f76f9f1) - 12:09 PM Revision 3ad211e2 (ceph): buildpackages: get Ceph git url via get_ceph_git_url()
- Instead of relying on git_base_url, use the get_ceph_git_url() to obtain
the URL of the Ceph repository to use with g... - 11:44 AM Revision 8bc89b65 (ceph): Merge pull request #581 from dachary/wip-11883-git-url
- buildpackages: get Ceph git url via get_ceph_git_url()
- 11:11 AM Revision 78b2a9aa (ceph): buildpackages: get Ceph git url via get_ceph_git_url()
- Instead of relying on git_base_url, use the get_ceph_git_url() to obtain
the URL of the Ceph repository to use with g... - 08:36 AM Backport #13252 (Resolved): mon: does not check for IO errors on every transaction
- https://github.com/ceph/ceph/pull/6091
- 05:24 AM Bug #12936 (Resolved): shec fails i386 make check
- 05:24 AM Revision bee3bdf5 (ceph): Merge pull request #6068 from dachary/wip-12936-shec
- erasure-code: shec must compare for equality with epsilon
Reviewed-by: Sage Weil <sage@redhat.com> - 05:23 AM Bug #13098 (Pending Backport): OSD crashed when reached pool's max_bytes quota
- We probably want to backport a simpler version of this patch that does not include the rados flags.
- 12:24 AM Bug #13098: OSD crashed when reached pool's max_bytes quota
- 05:22 AM Revision c571fd23 (ceph): Merge pull request #6052 from liewegas/wip-13098
- osd: fix full request handling
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 05:22 AM Revision 7ad2ac0f (ceph): Merge pull request #6075 from liewegas/wip-osd-getmap
- osd: avoid duplicate MMonGetOSDMap requests
Reviewed-by: Kefu Chai <kchai@redhat.com> - 05:19 AM Bug #13251 (Resolved): mon leaks lots on shutodwn
- two instances of mon.b leaking a zillion objects
description: rados/verify/{1thrash/none.yaml clusters/fixed-2.yam... - 12:24 AM Bug #13200 (Pending Backport): mon: does not check for IO errors on every transaction
- 12:23 AM Bug #13203 (Resolved): Error: Package: 1:ceph-radosgw-0.94.3-228.g2b11a4c.el7.x86_64 Requires: l...
- 12:16 AM Revision fdcfb79b (ceph): ceph-deploy: fix ceph-deploy-branch config options
- The config paramter of download_ceph_deploy does not have a ceph-deploy
item, therefore the ceph-deploy-branch parame...
09/25/2015
- 10:33 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/8042/consoleFull
- 08:11 AM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/8022/console
- 08:32 PM Bug #12983: handle_sub_read: Bad hash for 116/b1271c9d:test-rados-api-burnupi34-7183-66/foo/head
- 2015-09-24 22:48:12.489539 7ff05c984700 1 -- 10.214.132.108:6808/25735 <== client.4345 10.214.132.108:0/2866085996 1...
- 08:15 PM Bug #12983: handle_sub_read: Bad hash for 116/b1271c9d:test-rados-api-burnupi34-7183-66/foo/head
- Harumph, /a/sage-2015-09-24_20:43:22-rados-wip-sage-testing---basic-multi/1068002 has no recovery. This should be fa...
- 12:58 PM Bug #12983: handle_sub_read: Bad hash for 116/b1271c9d:test-rados-api-burnupi34-7183-66/foo/head
- The 'Bad hash' message triggered twice on my wip-sage-testing run that included the wip-12983 branch:
/a/sage-2015... - 06:31 PM rgw Bug #13239: Seg fault 9.0.3-1845-gf1ead76 : RGWRESTSimpleRequest::forward_request(RGWAccessKey&, ...
- Robin, see my fix at wip-13239.
- 06:14 PM rgw Bug #13239: Seg fault 9.0.3-1845-gf1ead76 : RGWRESTSimpleRequest::forward_request(RGWAccessKey&, ...
- The failure is in s3tests.functional.test_s3.test_region_bucket_create_secondary_access_remove_master actually, but I...
- 05:40 PM rgw Bug #13239: Seg fault 9.0.3-1845-gf1ead76 : RGWRESTSimpleRequest::forward_request(RGWAccessKey&, ...
- actually, the culprit is the following commit: abe4ec293d08b0314bf5c081ace2456073f3a22c
- 05:27 PM rgw Bug #13239: Seg fault 9.0.3-1845-gf1ead76 : RGWRESTSimpleRequest::forward_request(RGWAccessKey&, ...
- Yeah, I think I know what's happening and I see the issue. Something in the environment changed and it doesn't send t...
- 04:14 PM rgw Bug #13239 (Resolved): Seg fault 9.0.3-1845-gf1ead76 : RGWRESTSimpleRequest::forward_request(RGWA...
- Right after :s3tests.functional.test_s3.check_can_test_multiregion ..
http://qa-proxy.ceph.com/teuthology/teutholo... - 06:14 PM Revision 0cdc8d3a (ceph): Merge pull request #6077 from liewegas/wip-qa
- qa: http://ceph.com/qa -> http://download.ceph.com/qa
also some ceph.com/git -> git.ceph.com and a few line-endings -... - 06:01 PM Revision 216eef53 (ceph): Revert "osd: new pool settings: scrub intervals"
- This reverts commit 30810da4b573b3c7e679bc66eaa29b70246538cb.
After some discussion we have decided it is better to ... - 05:58 PM Backport #13245 (Resolved): client nonce collision due to unshared pid namespaces
- https://github.com/ceph/ceph/pull/6151
- 05:57 PM Backport #13244 (Resolved): client nonce collision due to unshared pid namespaces
- https://github.com/ceph/ceph/pull/6087
- 05:25 PM rgw Bug #13240: AssertionError: 31457280 != 30932992: s3tests.functional.test_s3.test_multipart_uploa...
- Note that it seems that all these type of failures (data length mismatch happen with the ec backend).
- 04:19 PM rgw Bug #13240 (Resolved): AssertionError: 31457280 != 30932992: s3tests.functional.test_s3.test_mult...
- quite a few failures due to this in rgw suite, one of the logs : http://qa-proxy.ceph.com/teuthology/teuthology-2015...
- 05:01 PM Revision 04679c54 (ceph): OSDMap: fill in known encode_features where possible
- Otherwise, if we get an incremental from hammer (struct_v = 6) we will
encode the full map as if it were before CEPH_... - 04:45 PM rgw Bug #13242 (Duplicate): rgw_readwrite: md5sum check failed original hash: �6�����:ï...
- md5sum checksum failure http://qa-proxy.ceph.com/teuthology/teuthology-2015-09-22_23:02:02-rgw-master---basic-multi/1...
- 04:29 PM rgw Bug #13241 (Duplicate): radosgw-admin assertion error: rgwlog['bucket'].find(bucket_name) == 0 o...
- description: rgw/singleton/{overrides.yaml all/radosgw-admin.yaml frontend/apache.yaml
rgw_pool_type/ec.yaml}
... - 04:04 PM rgw Bug #12661: radosgw-agent datasync S3ResponseError: 403 Forbidden dest_connection.get_bucket(buck...
- With recent master:
http://qa-proxy.ceph.com/teuthology/teuthology-2015-09-22_23:02:02-rgw-master---basic-multi/106... - 03:40 PM Revision 9c9514f7 (ceph): Merge pull request #6083 from jcsp/wip-mds-allow-star
- ceph-create-keys: set mds "allow *"
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 03:36 PM Bug #13238 (Duplicate): duplicate start of ceph-osd daemon
- OS:...
- 03:09 PM Revision c7e905e7 (ceph): ceph-create-keys: set mds "allow *"
- So that 'tell' works out of the box.
Signed-off-by: John Spray <john.spray@redhat.com> - 03:04 PM Revision f1f14f18 (ceph): erasure-code: shec must compare for equality with epsilon
- When comparing two double for strict inequality, a test for equality
using epsilon must also be done to ensure the re... - 02:03 PM CephFS Support #13211 (Closed): profiler and getting some memory info with it
- I think this got handled in irc.
- 01:39 PM CephFS Support #13211: profiler and getting some memory info with it
- there is only root, no other users. even i make it from localhost there is same error - 1 mds.0.39 handle_command: re...
- 08:24 AM CephFS Support #13211: profiler and getting some memory info with it
- Greg Farnum wrote:
> Apparently you're not using a client with enough caps on the MDS to give it instructions. The c... - 05:29 AM CephFS Support #13211: profiler and getting some memory info with it
- i made it even from mds node which i trying to get heap stats...so i guess problem here is not in a client...
what... - 01:41 PM Revision fe35ba3f (ceph): Merge pull request #5959 from mslovy/wip-current-dev
- mon: Fix unnecessary at/near max target warn in ceph -s
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Kefu C... - 01:39 PM Revision 13921221 (ceph): Merge pull request #5356 from majianpeng/code-cleanup
- osd: cleanup code when met crc error.
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:31 PM Revision ae7512dc (ceph): Merge pull request #5972 from Jerry7X/master
- unsigned type is short for journal max_size,use uint64_t instead
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-b... - 01:15 PM Bug #13208 (Fix Under Review): small probability sigabrt when setting rados_osd_op_timeout
- 12:59 PM Revision a2d80636 (ceph): Merge remote-tracking branch 'gh/infernalis'
- 12:56 PM Bug #13209 (Pending Backport): filestore: fix peek_queue for OpSequencer
- 12:56 PM Revision 892a2ade (ceph): Merge pull request #6048 from XinzeChi/wip-filestore-qlock
- filestore: fix peek_queue for OpSequencer
Reviewed-by: Sage Weil <sage@redhat.com> - 12:54 PM Bug #13089 (Pending Backport): mon: check for store writeablility before participating in election
- 12:53 PM Revision 9619c4a3 (ceph): Merge pull request #6040 from liewegas/wip-mon-kv
- mon: some fixes for kv backend failures
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Joao Eduardo Luis <jo... - 12:53 PM Bug #13032 (Pending Backport): client nonce collision due to unshared pid namespaces
- 12:53 PM Revision 28339fef (ceph): Merge pull request #6022 from jdurgin/wip-13032
- msg: randomize client nonces
Reviewed-by: Sage Weil <sage@redhat.com> - 12:52 PM Revision 4742f5d4 (ceph): Merge pull request #6012 from liewegas/wip-mon
- mon: misc scaling fixes
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:24 PM Revision 15e19a4a (ceph): client: refactor quota check functions
- Generalise the path traversal into check_quota_condition
and then call that from each of file_exceeded, bytes_exceede... - 12:24 PM Revision e52204cc (ceph): client: fix quote enforcement on subdir mounts
- While we don't allow setting quotas on the global
filesystem root, the inode which is root from the
client mount's po... - 11:16 AM Revision 273b4706 (ceph): Merge pull request #6027 from wido/mirror-docs
- docs: Update docs to make it clear that there are mirrors worldwide
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:12 AM RADOS Bug #13111: replicatedPG:the assert occurs in the fuction ReplicatedPG::on_local_recover.
- In my env, Many OSD crash because of it.
And I use aync msg. It seem like wrong send push_op to replicated.... - 06:09 AM RADOS Bug #13111: replicatedPG:the assert occurs in the fuction ReplicatedPG::on_local_recover.
- yes,only one osd crashed.i see it just once.But there is someone who joined ceph-devel encountered this problem
- 02:44 AM RADOS Bug #13111 (Need More Info): replicatedPG:the assert occurs in the fuction ReplicatedPG::on_local...
- Is this the only OSD that crashed? Have you seen it more than once?
- 05:47 AM Revision e7f277b8 (ceph): rgw/rgw_admin: Checking the legality of the params
- There is no messages When some params are invalid. so the Program should be added the function which checks params, i...
- 04:42 AM Revision f1d8a8f5 (ceph): Objecter: repeated free op->ontimeout.
- repeated free op->ontimeout in SafeTimer::timer_thread::callback->complete
Fixes: #13208
Signed-off-by: Ruifeng Yang... - 03:54 AM devops Bug #13204 (Resolved): gitbuilder broken symlink leading to 403 for 'wget http://gitbuilder.ceph....
- So I had an inspiration, and it worked:
1) set git.ceph.com's IP addr in /etc/hosts, so that git://ceph.com reall... - 03:42 AM Bug #13236: multiple kill commands lead to data lost when stoping ceph
- It's true that the repeat kill signals are probably not helpful, but killing the process like this (or sending it kil...
- 03:04 AM Bug #13236 (Won't Fix): multiple kill commands lead to data lost when stoping ceph
- when stoping ceph, multiple kill commands may be sended to one osd or monitor every one second at /etc/init.d/ceph. H...
- 03:37 AM Revision 910770c3 (ceph): releases/infernalis.yaml: final steps after infernalis upgrade
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:37 AM Revision 9e95c743 (ceph): upgrade/hammer-x/parallel: set infernalis settings after upgrade
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:34 AM Revision ecc504fe (ceph): tasks/divergent_priors2: wait for osd to start before tell
- Otherwise we can get
2015-09-24T19:22:15.191 INFO:teuthology.orchestra.run.mira080.stderr:Error ENXIO: problem getti... - 03:33 AM Revision 4a0e56f1 (ceph): tools/ceph-kvstore-tool: handle wrong command line argv
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:11 AM Revision ea5cea8e (ceph): rados/singleton-nomsgr/all/11429: more reliably create orphan pgs
- Make sure osds have the latest map with a pg ls
Signed-off-by: Sage Weil <sage@redhat.com> - 02:56 AM Revision e01dedb6 (ceph): Merge pull request #574 from ceph/wip-13098
- rados/singleton-nomsgr/all/full-tiering: test full cache tier
- 02:55 AM Revision cff9bddb (ceph): rados/singleton-nomsgr/all/full-tiering: test full cache tier
- Verify fix for #13098
Signed-off-by: Sage Weil <sage@redhat.com> - 02:49 AM Bug #13128: mixed client firefly osd with hammer client - rados api test failure
- The *NS tests are for an API that was added after firefly, so they are not expected to pass.
I assume this is the ... - 02:49 AM Bug #13128: mixed client firefly osd with hammer client - rados api test failure
- The *NS tests are for an API that was added after firefly, so they are not expected to pass.
I assume this is the ... - 02:27 AM rgw Documentation #13235 (Resolved): rgw: The command of [log show] show an incorrect usage according...
- When you use the command of [log show] with the option date in its default pattern, you will get an error output whic...
- 02:21 AM Revision 0635b135 (ceph): Objecter: maybe access wild pointer(op) in _op_submit_with_budget.
- look at "after giving up session lock it can be freed at any time by response handler" in _op_submit,
so the _op_subm... - 01:05 AM Revision 482d4e50 (ceph): AsyncConnection: Add new debug log
- Signed-off-by: Haomai Wang <haomai@xsky.com>
09/24/2015
- 11:27 PM Revision a1eb380c (ceph): osd/ReplicatedPG: fix ENOSPC checking
- 1. We need to return ENOSPC *before* we apply our side-effects to the obc
cache in finish_ctx().
2. Consider object ... - 11:13 PM Revision 1f2274e2 (ceph): osd/PG: set last_epoch_marked_full on map advance
- This will get persisted and shared.
Signed-off-by: Sage Weil <sage@redhat.com> - 11:13 PM Revision 8ffefecf (ceph): osd: do full check in do_op
- 1. The current pool_last_map_marked_full tracking is buggy.
2. We need to recheck this each time we consider the op, ... - 11:13 PM Revision 9c93ee30 (ceph): osd: remove buggy [pool_]last_map_marked_full tracking
- This is buggy (we reset the pool epoch each time it remains full instead
of only on the initial transition from non-f... - 11:13 PM Revision da7f3add (ceph): osd/osd_types: remove [pool_]last_epoch_marked_full from OSDSuperblock
- This is no longer used or needed.
Signed-off-by: Sage Weil <sage@redhat.com> - 11:13 PM Revision bf7e937a (ceph): osdc/Objecter: set FULL_FORCE flag when honor_full is false
- This currenty only applies to the MDS. Eventually we can remove the
OSD MDS checks once we are confident all MDS ins... - 11:13 PM Revision 79475d8e (ceph): osd/osd_types: add last_epoch_marked_full to pg_history_t
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:02 PM Revision 95055e70 (ceph): osd: add FULL_TRY and FULL_FORCE rados op flags
- FULL_TRY = try to do the op; ENOSPC if it results in a net increase is
space. client must cope.
FULL_FORCE = do the... - 10:36 PM Revision 7757342f (ceph): qa: https://ceph.com/git -> https://git.ceph.com
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:35 PM Bug #13234: dumpling incrementals do not work properly on hammer and newer
Dumpling OSDMap::Incremental encodings do not include encode_features. Hammer OSD::handle_osd_map when it attempts...- 10:34 PM Bug #13234 (Resolved): dumpling incrementals do not work properly on hammer and newer
- 10:35 PM Revision c5921333 (ceph): Merge pull request #6031 from s09816/master
- librbd:reads larger than cache size hang.
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Reviewed-by: Josh Durgin... - 10:24 PM rgw Bug #12629 (Resolved): the arguments 'domain' should not be assigned when return false
- 10:23 PM rgw Backport #12854 (Resolved): the arguments 'domain' should not be assigned when return false
- 10:22 PM rgw Bug #12630 (Resolved): segmentation fault when rgw_gc_max_objs > HASH_PRIME
- 10:21 PM rgw Backport #12855 (Resolved): segmentation fault when rgw_gc_max_objs > HASH_PRIME
- 10:17 PM rgw Backport #12592 (Resolved): RGW returns requested bucket name raw in "Bucket" response header
- 10:10 PM Revision d4d65fbd (ceph): qa: http://ceph.com/qa -> http://download.ceph.com/qa
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:02 PM Revision a3afb3f5 (ceph): rgw: remove trailing :port from host for purposes of subdomain matching
- Some clients (ahem, CrossFTP) include the :port in the HTTP_HOST header.
Strip it out.
Switch req_info field to a st... - 09:01 PM Revision fe0fc4f1 (ceph): Merge pull request #5715 from dachary/wip-12592-hammer
- RGW returns requested bucket name raw in Bucket response header
- 09:00 PM Revision e26f8bc2 (ceph): Merge pull request #5719 from dachary/wip-12855-hammer
- segmentation fault when rgw_gc_max_objs > HASH_PRIME
- 09:00 PM Revision 19e549e9 (ceph): Merge pull request #5720 from dachary/wip-12854-hammer
- the arguments 'domain' should not be assigned when return false
- 08:29 PM Backport #13233 (Resolved): mon: include min_last_epoch_clean as part of PGMap::print_summary and...
- https://github.com/ceph/ceph/pull/6152
- 08:21 PM CephFS Bug #12674 (Resolved): Semi-reproducible crash of ceph-fuse
- 08:18 PM rgw Bug #13022 (Duplicate): Ceph/Radosgw v0.94 Content-Type versus Content-type
- This appears to be a duplicate of #12939.
Hammer and firefly backports are in progress. - 08:12 PM CephFS Feature #13231: kclient: support SELinux
- IMHO, it might be the missing hooks like security_inode_init_security() calls.
- 08:03 PM CephFS Feature #13231: kclient: support SELinux
- Greg, from the first 2nd test, ceph fs was able to set xattr (thanks to #1878). But ceph failed to set security.secur...
- 07:43 PM CephFS Feature #13231: kclient: support SELinux
- See #5486, #1878, and others in the tracker — I think CephFS is ready for support now, but SELinux needs to get modif...
- 07:19 PM CephFS Feature #13231 (Duplicate): kclient: support SELinux
- I cannot set selinux labbels on ceph mount.
Environment:
[root@host16-rack08 ~]# modinfo ceph
filename: /l... - 08:09 PM rgw Backport #13224 (In Progress): rgw: fails to parse HTTP_HOST=<FQDN>:<PORT> header
- 10:48 AM rgw Backport #13224 (Resolved): rgw: fails to parse HTTP_HOST=<FQDN>:<PORT> header
- https://github.com/ceph/ceph/pull/6042
- 06:35 PM Feature #13198: mon: include min_last_epoch_clean as part of PGMap::print_summary and PGMap::dump
- https://github.com/guangyy/ceph/commit/f5359f2314ce3e76ed446c01889dd23550c3ac36
- 10:58 AM Feature #13198: mon: include min_last_epoch_clean as part of PGMap::print_summary and PGMap::dump
- What is the commit that needs backporting ?
- 06:35 PM CephFS Support #13211: profiler and getting some memory info with it
- Apparently you're not using a client with enough caps on the MDS to give it instructions. The client.admin key that's...
- 01:20 PM CephFS Support #13211: profiler and getting some memory info with it
- same situation with mds memory check onto virtual machines(same osd and mons check goes fine):
root@node1:~# ceph ... - 04:24 PM Bug #12665: osd/ReplicatedPG.cc: 2706: FAILED assert(p != snapset.clones.end())
- We are encountering the same issue after trying to delete a snapshot.
Here is a log file with debug osd = 20/20 (set... - 04:20 PM Revision 3736ca2a (ceph): Merge pull request #577 from ceph/wip-get-prop
- tolerate pg_num get failure
- 04:19 PM Revision 0e2814d8 (ceph): tasks/ceph_manager: ignore failure getting pg_num
- Otherwise, we may fail while racing with a workload that deletes a pool:
2015-09-23T15:01:52.855 INFO:tasks.workunit... - 03:38 PM Revision cdccf110 (ceph): osd/PG: compensate for sloppy hobject scrub bounds from hammer
- Hammer is sloppy about the hobject_t's it uses for the scrub bounds in that
the pool isn't set. (Hammer FileStore do... - 03:36 PM Revision acda626d (ceph): osd: avoid duplicate MMonGetOSDMap requests
- These are relatively expensive (we grab the full map from the mon) so we
should avoid duplicating our requests.
Trac... - 03:22 PM RADOS Bug #12733: cli: error connecting to cluster does not explain the problem
- attempt at it: https://github.com/ceph/ceph/pull/6074
- 02:54 PM rbd Bug #13164 (Fix Under Review): librbd: reads larger than cache size hang
- 02:19 PM Revision 18a985af (ceph): Merge pull request #6072 from yuyuyu101/update-org
- Update org
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:58 PM Revision f4bf14dd (ceph): Update Xinze affinity
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 01:57 PM Revision d50f5429 (ceph): Merge pull request #6066 from dachary/wip-ceph-detect-init
- build/ops: ceph-detect-init must ignore .cache
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:56 PM Revision eb28eeff (ceph): Update Chen Min affinity
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 01:55 PM Revision 58b8a8f2 (ceph): Update Tianshan affinity
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 01:53 PM Revision 58ad7b79 (ceph): Update Haomai Wang affinity
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 01:14 PM Revision 3ed6045d (ceph): docs: Update docs to make it clear that there are mirrors worldwide
- 12:49 PM rbd Bug #13156: import/export do not support snapshots
- export-diff / import-diff do preserve snapshots -- I think this is the tool you want to use.
- 12:48 PM rgw Bug #12407: With root as default user, unable to have multiple RGW instances running
- https://github.com/ceph/ceph/commit/68b5a8d10e46066d01aaecc42a29f6bbe6215a67
- 12:06 PM rgw Bug #12407: With root as default user, unable to have multiple RGW instances running
- What commit / pull requests fixes this issue ?
- 12:12 PM Revision 557df13b (ceph): tools/cephfs: detect malformed ESubtreeMap::expire_pos
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:12 PM Revision efdaa930 (ceph): mds: fix error reformatting subtreemap_test events
- Rare outside of vstart clusters, but if someone did
ever have one of these events in their journal and
try to update ... - 12:10 PM Backport #13195 (New): should recalc the min_last_epoch_clean when decode PGMap
- 12:09 PM rgw Backport #12918 (In Progress): RGW Swift API: response for GET on Swift account doesn't contain m...
- 12:09 PM Bug #13213: stuck recovering apparently due to pg_query not sent by async messenger?
- 1. osd.0 build a successful connection with osd.1:
osd.0 log
2015-09-23 01:22:38.594434 7f12ba4ef700 1 -- 10.214.1... - 12:08 PM rgw Backport #13228 (Resolved): rgw: segments are read during HEAD on Swift DLO
- https://github.com/ceph/ceph/pull/6160
- 12:07 PM rgw Backport #13227 (Resolved): With root as default user, unable to have multiple RGW instances running
- https://github.com/ceph/ceph/pull/6161
- 12:05 PM rgw Backport #13226 (Resolved): Keystone Fernet tokens break auth
- https://github.com/ceph/ceph/pull/6162
- 12:04 PM rgw Backport #13225 (Resolved): init script doesn't start daemon - errors silently
- https://github.com/ceph/ceph/pull/6161
- 10:47 AM rgw Bug #12353 (Pending Backport): rgw: fails to parse HTTP_HOST=<FQDN>:<PORT> header
- 10:11 AM Bug #12936 (Fix Under Review): shec fails i386 make check
- https://github.com/ceph/ceph/pull/6068
- 10:05 AM CephFS Feature #12334: nfs-ganesha: handle client cache pressure in NFS Ganesha FSAL
- Pinged Matt & Adam about this yesterday, Matt's planning to work on it at some stage. In some cases we may want to s...
- 09:48 AM Bug #12954: osd/osd_types.cc: 4074: FAILED assert(clone_size.count(clone))
- We are seeing the same bug after adding more OSDs:...
- 09:23 AM Revision 6f11b82f (ceph): Merge pull request #6063 from dachary/wip-tar-v7
- build/ops: make dist needs files with names > 99 characters
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:54 AM Revision 627756e0 (ceph): build/ops: ceph-detect-init must ignore .cache
- In case the test fails, it may leave files behind:
src/ceph-detect-init/.cache/v/cache/lastfailed
Signed-off-by: Lo... - 08:38 AM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- Running the test in a loop to reproduce it. If it does not happen in ~50 run, then it's probably a concurrency proble...
- 07:37 AM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/7998/console
- 08:35 AM Bug #12802: support of non-block connect in async messenger
- Kefu Chai wrote:
> https://github.com/ceph/ceph/pull/5681
change to https://github.com/ceph/ceph/pull/5848 - 08:08 AM Revision 2028ba2b (ceph): Merge pull request #5694 from guce/rgw_improve_key_operate
- rgw: improve convenience for key operate.
- 08:06 AM Revision 9c8200bb (ceph): librbd:reads larger than cache size hang.
- Fixes:#13164
Signed-off-by: Lu Shi <shi.lu@h3c.com> - 08:03 AM rgw Bug #13223 (Closed): Can’t reach quota limit when use multipart upload objects
- use multipart upload some object to bucket which enable bucket quota
I found that the number of objects can’t reach ... - 07:05 AM Bug #12100: OSD crash, uexpected aio error in FileJournal.cc
- How did you conclude that Sage?
Do you have any pointers on what can be done? - 06:21 AM Backport #13036: osd: avoid multi set osd_op.outdata in tier pool
- https://github.com/ceph/ceph/pull/6060
- 06:07 AM Revision 396702aa (ceph): build/ops: make dist needs files with names > 99 characters
- When running make distdir=ceph-9.0.3-1870-gfd861bb dist, a few files
have names longer than 99 characters and discard... - 06:04 AM Bug #13208: small probability sigabrt when setting rados_osd_op_timeout
- master PR https://github.com/ceph/ceph/pull/6064 and https://github.com/ceph/ceph/pull/6078
- 02:41 AM Revision 71a42f7c (ceph): bug fix: osd: avoid multi set osd_op.outdata in tier pool
- There are two read op on the same object for ec pool. First op read
miss happend, calling do_proxy_read and promote_o... - 02:22 AM Revision 5f7b3f5c (ceph): filestore: fix peek_queue for OpSequencer
- Fixes: #13209
Signed-off-by: Xinze Chi <xinze@xsky.com> - 02:09 AM Revision 6334d64c (ceph): rgw:mdlog trim add usage prompt
- Signed-off-by: Weijun Duan <duanweijun@h3c.com>
- 01:35 AM rbd Bug #13221 (Resolved): rbd-replay: cryptic error when 'rbd' pool does not exist
- By default rbd-replay tries to use the 'rbd' pool. It should print a better error message when the pool doesn't exist...
- 01:32 AM rbd Bug #13220 (Resolved): rbd-replay-prep: crashes on incorrect trace file
- A useful error message should be displayed instead of asserting when something like this is run:...
- 01:29 AM Bug #13219 (Can't reproduce): get_device_by_uuid->blkid_find_dev_with_tag() may hang for 3 min
- Date: Wed, 23 Sep 2015 22:48:07 +0000
From: Somnath Roy <Somnath.Roy@sandisk.com>
To: "Samuel Just (sam.just@inktan... - 12:59 AM devops Bug #13204: gitbuilder broken symlink leading to 403 for 'wget http://gitbuilder.ceph.redhat.com/...
- even more awesomeness: v0.80.8 had a submodule that pointed to ceph.com/git.
09/23/2015
- 11:20 PM Revision c0534990 (ceph): osd/: eliminate unnecessary pg_hit_set_history_t::current_info
- The only field actually relevant from this structure is .begin, which
duplicates the information in hit_set_start_sta... - 11:18 PM Bug #13217 (Rejected): ceph-osd: common/Formatter.cc:230: virtual void ceph::JSONFormatter::close...
- Just kidding, bug in my branch.
- 11:01 PM Bug #13217 (Rejected): ceph-osd: common/Formatter.cc:230: virtual void ceph::JSONFormatter::close...
- 2015-09-22T22:44:08.409 INFO:tasks.ceph.osd.2.burnupi19.stderr: in thread 7f3f1ab7a700
2015-09-22T22:44:08.416 INFO:... - 11:17 PM devops Bug #13204: gitbuilder broken symlink leading to 403 for 'wget http://gitbuilder.ceph.redhat.com/...
- (and we still want to test from v0.80.8 -> later versions, because v0.80.8 had a specific sort of pg breakage)
- 11:17 PM devops Bug #13204: gitbuilder broken symlink leading to 403 for 'wget http://gitbuilder.ceph.redhat.com/...
- So the upshot here is that the build was broken and never fixed in v0.80.8; rpmbuild now complains because of a chang...
- 08:55 PM devops Bug #13204: gitbuilder broken symlink leading to 403 for 'wget http://gitbuilder.ceph.redhat.com/...
- On @gitbuilder-archive@:...
- 08:44 PM devops Bug #13204: gitbuilder broken symlink leading to 403 for 'wget http://gitbuilder.ceph.redhat.com/...
- http://gitbuilder.ceph.com/ceph-rpm-centos7-x86_64-basic/ref/v0.80.8/ yields a 403 instead of a 404, which would be c...
- 02:59 AM devops Bug #13204 (Resolved): gitbuilder broken symlink leading to 403 for 'wget http://gitbuilder.ceph....
- Rados hammer singleton-nomsgr test failure, either the version should be modified in config.yaml( 0.80.8 to firefly )...
- 10:59 PM Bug #13216 (Duplicate): import/export bug: ceph_test_rados read incorrect buffer
- Caused by import/export causing updates to be lost. Might consider working around by limiting objectstore tool tests...
- 09:18 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/7988/console
- 05:33 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- For archive, to get a better idea of the frequency, I'm recording all occurrences http://jenkins.ceph.dachary.org/job...
- 04:31 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- This is an interesting occurrence : http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/7976/console as ...
- 03:29 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- It looks like running the test about a 100 times is going to trigger the problem reliably.
- 03:23 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/7968/console
- 06:35 AM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/7951/console
- 09:09 PM Bug #13088 (Resolved): a73a4cb breaks "--without-libatomic-ops" (firefly)
- 09:09 PM Revision ecabc679 (ceph): Merge pull request #6038 from liewegas/wip-13088
- common/HeartBeat: include types
Reviewed-by: Kefu Chai <kchai@redhat.com> - 09:06 PM Revision 2e09a2c2 (ceph): common/RWLock: include assert
- Fixes atomic_t build issue without libatomic-ops.
Fixes: #13088
Signed-off-by: Sage Weil <sage@redhat.com> - 09:00 PM Revision fd861bb2 (ceph): Merge pull request #6053 from ceph/wip-cmake-dang
- Wip cmake dang
- 08:59 PM Feature #13198 (Pending Backport): mon: include min_last_epoch_clean as part of PGMap::print_summ...
- 08:59 PM Revision 2805246a (ceph): Merge pull request #6056 from guangyy/wip-13198
- osd: print min_last_epoch_clean along with pg dump
Reviewed-by: Sage Weil <sage@redhat.com> - 07:37 PM Revision ce003354 (ceph): Merge pull request #576 from ceph/wip-13031-packages
- buildpackages: make rpm packages
Reviewed-by: Joe Julian <jjulian@io.com> - 07:31 PM Bug #13214: ceph upstart script rbdmap.conf incorrectly processes parameters
- Correction, the fix is to make sure CMDPARAMS is reset for each new set of parameters being processed:...
- 07:28 PM Bug #13214 (Resolved): ceph upstart script rbdmap.conf incorrectly processes parameters
- The upstart script for mapping rbd devices incorrectly creates the "CMDPARAMS" value such that it becomes cumulative ...
- 07:26 PM Bug #13203 (Fix Under Review): Error: Package: 1:ceph-radosgw-0.94.3-228.g2b11a4c.el7.x86_64 Req...
- 07:26 PM Bug #13203: Error: Package: 1:ceph-radosgw-0.94.3-228.g2b11a4c.el7.x86_64 Requires: libfcgi.so.0...
- This might fix it: https://github.com/ceph/ceph-cm-ansible/pull/140
(Longer-term, we should simply enable EPEL dur... - 07:20 PM Bug #13203: Error: Package: 1:ceph-radosgw-0.94.3-228.g2b11a4c.el7.x86_64 Requires: libfcgi.so.0...
- If this is a test with Ceph upstream (it looks like this was done with a gitbuilder package), then EPEL needs to be e...
- 12:53 AM Bug #13203: Error: Package: 1:ceph-radosgw-0.94.3-228.g2b11a4c.el7.x86_64 Requires: libfcgi.so.0...
- Many failures here: http://pulpito.ceph.redhat.com/teuthology-2015-09-18_18:00:01-rbd-hammer-distro-basic-magna/
- 12:52 AM Bug #13203 (Resolved): Error: Package: 1:ceph-radosgw-0.94.3-228.g2b11a4c.el7.x86_64 Requires: l...
- There are quite a few failures related to this dependency issue in rbd suite, it might need some additional packages ...
- 07:16 PM Bug #13209: filestore: fix peek_queue for OpSequencer
- 07:13 PM Bug #13209: filestore: fix peek_queue for OpSequencer
- https://github.com/ceph/ceph/pull/6048
- 11:49 AM Bug #13209 (Resolved): filestore: fix peek_queue for OpSequencer
- when peek_queue, we should get the lock first.
- 07:11 PM Revision 7e3a271a (ceph): buildpackages: make rpm packages
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:08 PM Revision 704cd5d3 (ceph): Merge remote-tracking branch 'gh/wip-aarch64'
- 07:06 PM Revision 97d64b4e (ceph): Merge pull request #573 from ceph/wip-hammer-x
- hammer-x fixes
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 07:06 PM Revision 8087095f (ceph): upgrade/hammer-x/stress-split-erasure-code-x86_64: specify arch
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:52 PM Bug #13213: stuck recovering apparently due to pg_query not sent by async messenger?
- ceph-osd.sorted contains the osd logs sorted together fyi.
- 06:51 PM Bug #13213 (Resolved): stuck recovering apparently due to pg_query not sent by async messenger?
- pg 0.b7 seems to be stuck due to a pg_query not getting sent by async messenger.
Interval starts around 2015-09-23... - 04:30 PM CephFS Feature #12334: nfs-ganesha: handle client cache pressure in NFS Ganesha FSAL
- It looks like the ganesha FSAL interface already includes the function `up_async_invalidate` for this sort of thing, ...
- 04:02 PM devops Feature #13063 (Resolved): cobbler/ansible: put inktank-rescue image in cobbler-profiles role
- 03:58 PM Revision f5359f23 (ceph): osd: print min_last_epoch_clean along with pg dump
- Fixes: 13198
Signed-off-by: Guang Yang <yguang@yahoo-inc.com> - 03:19 PM Revision b20b7a9a (ceph): doc: rm another reference to Ceph Extras
- http://tracker.ceph.com/issues/13162 Refs: #13162
Signed-off-by: Ken Dreyer <kdreyer@redhat.com> - 03:01 PM Bug #13116: osd: pg stuck in replay
- 03:00 PM Bug #13200: mon: does not check for IO errors on every transaction
- 02:58 PM Revision ef909ccb (ceph): mon/Elector: do a trivial write on every election cycle
- Currently we already do a small write when the *first* election in
a round happens (to update the election epoch). I... - 02:58 PM Revision 2fb7b1f0 (ceph): mon/MonitorDBStore: assert/crash if there is a write error
- Do this globally intead of relying on teh zillion mon callers to
check the error code. There are no cases where we w... - 02:55 PM Revision 0b270246 (ceph): CMake - fix check for FUSE
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision b1401e51 (ceph): CMake - fix check for UDEV
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision b02e0f9b (ceph): CMake - fix libatomic_ops and gperftools checks
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision dcf647ec (ceph): CMake - fix check for NSS
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision a7ce8f5d (ceph): CMake - Add check for keyutils
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision cb7fe458 (ceph): CMake - fix check for expat
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision a18b649c (ceph): CMake - fix check for leveldb
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision 88f7df7d (ceph): CMake - add check for libuuid
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision a6c8b461 (ceph): CMake - fix check for fcgi
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision 1a4262c3 (ceph): CMake - add check for libcurl
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision 6adf1cbb (ceph): CMake - fix check for blkid
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision 571215ef (ceph): CMake - fix check for AIO
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision 3570dd56 (ceph): CMake - add check for XFS
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision 4d02f874 (ceph): CMake - fix check for Snappy
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM Revision a866a894 (ceph): CMake - add check for libedit
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 02:55 PM CephFS Support #13211: profiler and getting some memory info with it
- p.s.
mon and ceph info works fine:
ceph tell osd.0 heap stats
ceph tell mon.mon00 heap stats - 02:26 PM CephFS Support #13211 (Closed): profiler and getting some memory info with it
- ceph version 0.94.3 (95cefea9fd9ab740263bf8bb4796fd864d9afe2b)
3.13.0-61-generic #100-Ubuntu 2015 x86_64 x86_64 x86... - 02:46 PM Revision 3afd5178 (ceph): Merge remote-tracking branch 'gh/infernalis'
- 02:10 PM Backport #13210: tests : Fixed broken Makefiles after integration of lttng into rados
- Backport https://github.com/sponce/ceph/commit/e4c27d804834b4a8bc495095ccf5103f8ffbcc1e to Hammer to fix the LTTng du...
- 02:09 PM Backport #13210 (Resolved): tests : Fixed broken Makefiles after integration of lttng into rados
- https://github.com/ceph/ceph/pull/6322
- 12:20 PM Revision 3123b2c5 (ceph): arch/arm: s/false/0/
- arch/arm.c: In function 'ceph_arch_arm_probe':
arch/arm.c:54:28: error: 'false' undeclared (first use in this functio... - 11:40 AM Revision 66d19c78 (ceph): rgw: fix swift API returning incorrect account metadata
- Fixes: #13140
Fix the bug that swift account stat command returns doubled object count and bytes used
Signed-off-by... - 11:16 AM Bug #13208 (Resolved): small probability sigabrt when setting rados_osd_op_timeout
- ...
- 10:41 AM rgw Bug #13207: CVE-2016-7031 rgw: Anonymous user is able to read bucket with authenticated read ACL
- attatching test code
- 10:39 AM rgw Bug #13207 (Resolved): CVE-2016-7031 rgw: Anonymous user is able to read bucket with authenticate...
- When "authenticated-read" ACL is applied on a bucket; anonymous user is also able to read (eg. list) the bucket. But ...
- 09:11 AM rbd Bug #13164: librbd: reads larger than cache size hang
- https://github.com/ceph/ceph/pull/6031
- 08:15 AM Bug #13206 (Resolved): OSD::do_recovery() local variable "started" shall be explicitly initialize...
- void OSD::do_recovery(PG *pg, ThreadPool::TPHandle &handle)
int started;
bool more = pg->start_... - 08:01 AM Revision 7fbd70b6 (ceph): suites/fs: test ceph-fuse with 32-bits ino_t
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 07:17 AM CephFS Bug #12674: Semi-reproducible crash of ceph-fuse
- I can confirm that the issue is gone with the latest ceph source from Git. Sorry for taking so long to build and test...
- 06:30 AM Backport #13205 (Resolved): ReplicatedBackend: populate recovery_info.size for clone (bug symptom...
- https://github.com/ceph/ceph/pull/6153
- 06:01 AM Bug #13074: tcmalloc segfaults in Pipe::writer() when bufferlist goes out of scope
- "This occurred on a system under moderate load - has not happened since and I do not know how to reproduce."
- 03:49 AM rgw Fix #10927 (Pending Backport): init script doesn't start daemon - errors silently
- This affects hammer and we should get the patch (https://github.com/ceph/ceph/pull/5325) into a future hammer release.
- 03:20 AM CephFS Bug #13166: MDS: standby-replay does not change client_incarnation properly
- For firely, standby-replay MDS also uses 0 as client_incarnation, its ID is MDS.x.0.
- 01:15 AM CephFS Bug #13166: MDS: standby-replay does not change client_incarnation properly
- Zheng, can you dig up a firefly test run and make sure the behavior of standby-replay daemons there is the same as it...
- 02:56 AM Bug #13114: LibRadosWatchNotify.WatchNotify2Timeout
- /a/kchai-2015-09-22_03:49:41-rados-wip-kefu-testing---basic-multi/1064089/ seems like a different one though.
- 02:40 AM Bug #13089 (Fix Under Review): mon: check for store writeablility before participating in election
- https://github.com/ceph/ceph/pull/6040
- 02:12 AM rgw Bug #13022: Ceph/Radosgw v0.94 Content-Type versus Content-type
- This gets fixed in the master already but not backported yet: 1b9fbffdc24160251b96cec820d62fb2a12b6eab
- 01:52 AM Revision cb2fc29c (ceph): rgw: refuse to calculate digest when the s3 secret key is empty
- Fixes: #13133
Refuse to calculate the s3 header digest when the secret key is empty so that it cannot pass authentic... - 01:52 AM Revision 7e5980b4 (ceph): rgw: improve convenience for key operate.
- 1.key-type assignments based on context if it wasn't specified
In user operate context, key-type assignment to KEY... - 12:40 AM Revision 36e4a80c (ceph): ReplicatedPG::hit_set_setup: fix hit_set_remove_all call
- We only want to do it if the pool config changed AND we are
primary && active.
fd38902dd4693b9b72f7532833e78f5df2c9e... - 12:39 AM Revision 8e5a801b (ceph): osd/: assert in HitSet constructor if type is TYPE_NONE as well
- Otherwise impl is unpopulated and we risk segfaults in several
methods. It also seems like it would always indicate ...
09/22/2015
- 11:32 PM rbd Bug #13156: import/export do not support snapshots
- I try to add a feature about this:
http://tracker.ceph.com/issues/13186 - 11:30 PM rbd Bug #13156: import/export do not support snapshots
- Sage Weil wrote:
> import/export do not preserve snapshots.
but could I add a feature about "--with-snap", so it ... - 02:48 PM rbd Bug #13156 (Won't Fix): import/export do not support snapshots
- import/export do not preserve snapshots.
- 11:30 PM Bug #13074: tcmalloc segfaults in Pipe::writer() when bufferlist goes out of scope
- I've asked the original reporter of this issue to add any information he can.
- 07:37 PM Bug #13074: tcmalloc segfaults in Pipe::writer() when bufferlist goes out of scope
- This looks like heap corruption or use-after-free or similar. How how do you reproduce it?
- 02:57 PM Bug #13074 (Need More Info): tcmalloc segfaults in Pipe::writer() when bufferlist goes out of scope
- We'll need more information about the conditions this occurred in.
- 10:42 PM rgw Backport #13019 (In Progress): rgw: intra region copy does not preserve acl
- 08:05 PM rgw Backport #13019: rgw: intra region copy does not preserve acl
- pull requet: https://github.com/ceph/ceph/pull/6039
- 09:53 PM Revision ef973051 (ceph): cls_rgw: fix bucket listing when dealing with invisible entries
- Fixes: #12913
The bucket listing logic was broken when dealing with invisible entries.
Need to read keys until we ca... - 09:19 PM rgw Bug #12353: rgw: fails to parse HTTP_HOST=<FQDN>:<PORT> header
- Hammer backport PR at https://github.com/ceph/ceph/pull/6042
- 08:41 PM Bug #13098 (Fix Under Review): OSD crashed when reached pool's max_bytes quota
- -https://github.com/ceph/ceph/pull/6041-
- 07:52 PM Bug #13098: OSD crashed when reached pool's max_bytes quota
- Easily reproduced on hammer.
- 08:24 PM Bug #13200 (Duplicate): mon: does not check for IO errors on every transaction
- https://github.com/ceph/ceph/pull/6040
- 08:10 PM rgw Bug #11563: RadosGW regression: COPY doesn't preserve Content-Type
- Sorry for the time it takes. It fixed a regression but also introduced one, so we need to make sure everything works ...
- 08:05 PM rgw Backport #12852: test_s3.test_object_copy_canned_acl ... FAIL
- A new pull request: https://github.com/ceph/ceph/pull/6039
- 08:04 PM rgw Backport #12199: RadosGW regression: COPY doesn't preserve Content-Type
- I created a new pull request: https://github.com/ceph/ceph/pull/6039
- 08:03 PM Revision b9f2ed30 (ceph): rgw: don't preserve acls when copying object
- Fixes: #12370
When copying an object we need to use the acls we calculated earlier,
and not the source acls.
This wa... - 08:03 PM Revision 77cb503b (ceph): rgw: preserve all attrs if intra-zone copy
- Fixes: #13015
Intra zone copy requires that all objects' attributes are preserved.
Signed-off-by: Yehuda Sadeh <yehu... - 07:45 PM Bug #13075: ms async: msg throttle busy loops?
- Sage Weil wrote:
> The run didn't finish so teuthology didn't gather logs.. i should have done that manually :(. Ig... - 07:39 PM Bug #13075 (Can't reproduce): ms async: msg throttle busy loops?
- Haomai Wang wrote:
> Why I don't find "remote" dir at /a/sage-2015-09-12_17:44:29-rados-wip-sage-testing---basic-mul... - 07:35 PM Bug #13130 (Resolved): qa:failed pool create in mkpool_layout_vxattrs.sh
- the run didn't include commit:524b0bdcc45c2f4b95f2239c988e93250f337f3d
- 07:31 PM Bug #13088 (Fix Under Review): a73a4cb breaks "--without-libatomic-ops" (firefly)
- https://github.com/ceph/ceph/pull/6038
- 07:12 PM rgw Bug #12407 (Pending Backport): With root as default user, unable to have multiple RGW instances r...
- 06:15 PM rgw Bug #12407 (Fix Under Review): With root as default user, unable to have multiple RGW instances r...
- 07:12 PM Revision 68b5a8d1 (ceph): Merge pull request #6037 from liewegas/wip-12407
- init-radosgw: fix restart w/ multiple instances
Reviewed-by: Pavan Rallabhandi <pavan.rallabhandi@sandisk.com> - 06:44 PM Revision d422f282 (ceph): OSDService::agent_entry: don't use PG::operator<< without pg lock
- Fixes: #13199
Signed-off-by: Samuel Just <sjust@redhat.com> - 06:43 PM Bug #13199 (Resolved): segfault in agent_work
- ...
- 06:42 PM Bug #13194 (Resolved): can't find python-flask during upgrade
- 06:42 PM Bug #13194: can't find python-flask during upgrade
- switched to centos (distros/supported) isntead of hard-coded rhel
- 05:20 PM Bug #13194: can't find python-flask during upgrade
- the package is at
http://apt-mirror.front.sepia.ceph.com/rhel7repo/extras/rhel-7-server-extras-rpms/ so hopefully t... - 06:29 PM Revision f1ead76f (ceph): Merge pull request #5928 from ceph/wip-12819-infernalis
- Wip 12819 infernalis
- 06:27 PM Revision 8e6bf15f (ceph): Merge pull request #6006 from dachary/wip-12936-shec
- erasure-code: workaround i386 optimization bug with SHEC
Reviewed-by: Sage Weil <sage@redhat.com> - 06:21 PM rgw Bug #9001 (Won't Fix): Starting gateway with radosgw init script fails to create socket
- 06:20 PM rgw Bug #5378 (Resolved): make radosgw-admin user rm idempotent
- https://github.com/ceph/ceph/pull/5918
- 06:15 PM rgw Bug #12920 (Duplicate): HEAD requests on large MPU Swift objects consistently timeout
- Duplicate of #12780
- 06:13 PM Revision e17c8e1a (ceph): init-radosgw: specify pid file to start-stop-daemon
- This fixes restart when multiple instances are running.
Fixes: #12407
Tested-by: Pavan Rallabhandi <pavan.rallabhand... - 06:04 PM Revision fb5f058a (ceph): Merge remote-tracking branch 'gh/infernalis'
- 06:03 PM Bug #13116 (Fix Under Review): osd: pg stuck in replay
- https://github.com/ceph/ceph/pull/6036
- 06:00 PM Revision d18cf51d (ceph): osd: fix requeue of replay requests during activating
- If the replay period expires while we are still in the activating
state, we can simply insert our list of requests at... - 05:58 PM Feature #13198 (Resolved): mon: include min_last_epoch_clean as part of PGMap::print_summary and ...
- Copy from the IRC to track the enhancement:...
- 05:40 PM Revision a653f6c0 (ceph): Merge pull request #571 from dachary/wip-isa-arch
- erasure-code: isolate isa plugin arch constraint
- 05:25 PM rgw Bug #13197 (Rejected): rgw: creating user by admin api returns 403 access deny
- Having added caps of "users=*" to an admin user, I can neither create nor delete a user by admin op api.
user info... - 05:24 PM Revision 1e5b352d (ceph): upgrade/hammer-x: use supported distros, not hard-coded rhel7+trusty
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:06 PM Bug #13196 (Resolved): .gitmodules have ceph.com/git (firefly)
- 10:30 AM Bug #13196 (Resolved): .gitmodules have ceph.com/git (firefly)
- They must be replaced with git.ceph.com
http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-rpm-centos7-amd64-notcmal... - 05:04 PM Revision 741dd5b9 (ceph): .gitmodules: fix ceph-object-corpus source url
- Fixes: #13196
Signed-off-by: Sage Weil <sage@redhat.com> - 04:32 PM Revision 424bcea9 (ceph): Merge pull request #5922 from trociny/wip-pool-set-noscrub
- osd: per pool control for scrub and deep-scrub
Reviewed-by: David Zafman <dzafman@redhat.com> - 04:29 PM Revision a1997879 (ceph): Merge pull request #6000 from SUSE/wip-12097-firefly
- kernel_untar_build fails on EL7
- 04:28 PM Bug #13089: mon: check for store writeablility before participating in election
- Can we have a bit more context please? What's the rationale behind this? The monitor should not start if leveldb is n...
- 02:58 PM Bug #13089: mon: check for store writeablility before participating in election
- Greg Farnum wrote:
> Mmm, I'm not sure we want to do the naive thing (write a file and fsync) on every election as t... - 03:54 PM Revision 44a2609d (ceph): Merge pull request #5846 from xiexingguo/xxg-wip-13002
- msg/simple: start over after fails to bind a port in specified range
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:33 PM Revision 88cffd87 (ceph): rgw: don't treat Content-Type as automatically dumpable metadata.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 03:26 PM Revision 58453d3f (ceph): upgrade/hammer-x/point-to-point: fix x client
- - install hammer for hammer->x upgrade
- use hammer branch for workunit
Signed-off-by: Sage Weil <sage@redhat.com> - 03:26 PM Revision bc9a66c7 (ceph): upgrade/hammer-x/parallel: clients are hammer to for final workload
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:26 PM Revision 91b11725 (ceph): upgrade/hammer-x: use rgw civetweb
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:17 PM Bug #13057: python-setuptools is missing from debian/control
- yes, otherwise the compilation wouldn't have succeeded that far.
- 02:55 PM Bug #13057 (Need More Info): python-setuptools is missing from debian/control
- did you ./install-deps.sh before building ?
- 02:57 PM Bug #12941 (New): mon/OSDMonitor.cc: 204: FAILED assert(err == 0) 0.94
- 02:54 PM Bug #13061: systemd: daemons restart when package is upgraded
- this may explain part of the problem with #13000, I'll try to repeat that
- 02:53 PM Bug #13061 (In Progress): systemd: daemons restart when package is upgraded
- 02:54 PM Bug #13090 (Resolved): ceph health detail format error in the mds0: line
- 02:52 PM Bug #13135 (Rejected): high mon memory usage after upgrade firefly -> hammer
- 600mb is not unreasonable; the default leveldb cache size is 512mb. you can adjust that down if you like!
- 02:52 PM Feature #13084: ceph-disk: will not work with an software array (md) as journal destination
- support for devicemapper has improved for multipath and dmcrypt devices, but there is not yet support for all possibl...
- 02:50 PM Bug #13119 (Can't reproduce): msg/async: does not wake up from standby?
- 02:49 PM Bug #13113 (Duplicate): common/Mutex.cc: 105: FAILED assert(r == 0)
- #13176
- 02:46 PM Bug #13175 (Resolved): Documentation promises backports to EOL release (Dumpling)
- 02:46 PM Bug #12179 (Duplicate): osd: PG.cc: FAILED assert(info.last_epoch_started >= info.history.last_ep...
- 02:45 PM Bug #12517 (Duplicate): assert failure in Objecter::_finish_op(Objecter::Op*)
- This was fixed, #10372. Fixed in later firefly and in hammer, but we didn't backport the fix to giant.
- 02:45 PM Bug #12013 (Can't reproduce): assert(info->on_notify_finish) in Objecter::handle_watch_notify(MWa...
- 02:42 PM Bug #8752: firefly: scrub/repair stat mismatch
- Exactly what stat mismatch are you seeing?
- 02:41 PM Bug #12862 (Won't Fix): ceph daemon does not generate core file on CentOS 7
- woudl rather focus on getting the systemd stuff correct for infernalis. unless you have a patch that fixes this?
- 02:40 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- and again http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/7923/console
it's weird that it was quiet... - 02:22 PM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- I have never seen this.
- 09:39 AM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- One more http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/7911/console
- 06:05 AM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- One more occurrence: https://github.com/ceph/ceph/pull/6011#issuecomment-142161738 and http://jenkins.ceph.dachary.or...
- 02:39 PM Bug #13004 (Resolved): OSD deadlocked.
- https://github.com/ceph/ceph/pull/5870
- 02:37 PM Bug #13104 (Rejected): osd: slow requests stuck for a long time
- This isn't really a bug so much as a desire for a difference in how we handle recovery, I think. Reopen as a feature...
- 02:34 PM Bug #12100 (Rejected): OSD crash, uexpected aio error in FileJournal.cc
- This is a hardware problem--we are correct in failing in this case.
- 02:33 PM Revision 42643589 (ceph): erasure-code: workaround i386 optimization bug with SHEC
- http://tracker.ceph.com/issues/12936 Fixes: #12936
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 02:32 PM Bug #12828 (Pending Backport): ReplicatedBackend: populate recovery_info.size for clone (bug symp...
- 02:32 PM Bug #12828 (Resolved): ReplicatedBackend: populate recovery_info.size for clone (bug symptom is s...
- 02:32 PM Bug #12936 (In Progress): shec fails i386 make check
- 02:31 PM Bug #13000 (In Progress): ceph-disk failure to activate with dmcrypt
- 02:23 PM Bug #13000 (Fix Under Review): ceph-disk failure to activate with dmcrypt
- 02:30 PM Messengers Bug #13072 (Need More Info): osd_ping messages not getting through
- 02:29 PM Bug #13143 (Resolved): incorrect buffer at pos 517268
- 02:29 PM Revision 4b71a546 (ceph): Merge pull request #5999 from dachary/wip-13000-ceph-disk
- ceph-disk: fixes various race conditions
Reviewed-by: Sage Weil <sage@redhat.com> - 02:28 PM Bug #13180 (Resolved): ceph-disk: --verbose --log-stdout trims --verbose
- 02:28 PM Bug #13174 (Resolved): ceph-disk: trigger /dev/dm-1 gets /dev/dm/1 instead
- 02:28 PM Bug #13160 (Resolved): ceph-disk: duplicate osd mount points
- 02:28 PM Bug #13157 (Resolved): ceph-disk: list fails on isolated journals
- 02:25 PM Fix #13154 (Resolved): ceph-disk: list /dev/vdb does not filter as expected
- 02:25 PM Bug #13153 (Resolved): ceph-disk: blkid 2.23.2 fails on journal device on CentOS 7
- 02:25 PM Bug #12787 (Resolved): ceph-disk does not activate with systemd on some CentOS 7
- 02:25 PM Bug #13150 (Resolved): Error: oid 223 read returned error code -2
- 02:24 PM Bug #13190 (Resolved): osd/ReplicatedPG.cc: 7247: FAILED assert(agent_state)
- 02:24 PM Revision 008cdd7c (ceph): Merge pull request #6008 from liewegas/wip-13190
- osd/ReplicatedPG: tolerate promotion completion with stopped agent
Reviewed-by: Samuel Just <sjust@redhat.com> - 02:22 PM Bug #11512 (Can't reproduce): "FAILED assert(0 == "unexpected error")" in upgrade:giant-x-hammer-...
- I don't think this new information is related to the old reports. If you think the daemon is corrupting the store wh...
- 06:35 AM Bug #11512: "FAILED assert(0 == "unexpected error")" in upgrade:giant-x-hammer-distro-basic-vps run
- Sage Weil wrote:
> I would expect a different error if we hit the fd limit, but... does using the init script stop... - 01:49 PM CephFS Bug #13129 (Rejected): qa: not starting ceph-mds daemons
- 01:39 PM Revision f4b55f46 (ceph): journaler: detect unexpected holes in journal objects
- Fixes: #13167
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 01:32 PM Revision c93008fb (ceph): Merge pull request #6011 from liewegas/wip-systemd
- systemd: increase nproc ulimit
- 12:29 PM Revision 0a3b5ddf (ceph): Merge pull request #6019 from liewegas/wip-mon-dispatch-debug
- mon/PaxosService: include msg and con ptr in dispatch debug
- 12:15 PM rgw Bug #11241 (Fix Under Review): Incorrect ETAG calculated for POST uploads
- Pull request: https://github.com/ceph/ceph/pull/6030.
- 12:14 PM rgw Bug #11241 (In Progress): Incorrect ETAG calculated for POST uploads
- 09:48 AM Revision 742906ab (ceph): rgw: fix wrong etag calculation during POST on S3 bucket.
- Fixes: #11241
Backport: infernalis, hammer, firefly
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> - 09:16 AM rgw Bug #12640: radosgw + civetweb latency issue on Hammer
- I am faced with the same issue, with AWS Java SDK based S3 client.
Looking at the packet trace, I found that this ... - 08:33 AM CephFS Bug #13167 (Fix Under Review): mds: replay gets stuck (on out-of-order journal replies?)
- 08:33 AM CephFS Bug #13167: mds: replay gets stuck (on out-of-order journal replies?)
- https://github.com/ceph/ceph/pull/6025
- 07:13 AM rbd Bug #13124 (Resolved): librbd order limits inconsistent with rbd cli
- If you can reproduce the 'rbd rm' failing from the original description, please open another bug. Closing this one fo...
- 12:45 AM rbd Bug #13124: librbd order limits inconsistent with rbd cli
- https://github.com/ceph/ceph/pull/5956
- 12:44 AM rbd Bug #13124 (Fix Under Review): librbd order limits inconsistent with rbd cli
- 07:07 AM Revision 6799f44f (ceph): Merge pull request #5956 from xinxinsh/wip-13124
- unify order limit
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:46 AM Revision c86438cd (ceph): ceph-disk: ensure udev add on the data partition is last
- When calling partprobe, we make sure there is at least one udev add
called for each partition created when preparing ... - 06:46 AM Revision 22a1f4cf (ceph): ceph-disk: reduce debug verbosity
- There is no need for debug traces from which() and it is very
noisy. Just get rid of it.
Signed-off-by: Loic Dachary... - 06:46 AM Revision b6470382 (ceph): tests: doc: ceph-disk workunit reminders
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 06:46 AM Revision d4d5153c (ceph): tests: ceph-disk: use sh() instead of helper() when possible
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 06:46 AM Revision d24f1f10 (ceph): tests: ceph-disk: multipath now auto activates
- http://tracker.ceph.com/issues/12786 Refs: #12786
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 06:46 AM Revision 46a3c93a (ceph): tests: ceph-disk: race condition is fixed
- It turns out it was not CentOS 7 specific. There is no excuse to skip
the tests anymore.
http://tracker.ceph.com/iss... - 06:46 AM Revision 24b3a800 (ceph): tests: ceph-disk: wait for the OSD to be up
- After preparing an OSD, wait for the corresponding OSD to be up
according to ceph osd dump before asserting the devic... - 06:46 AM Revision fb4dd7d4 (ceph): tests: ceph-disk: inline run_osd
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 06:46 AM Revision 0cf0e88e (ceph): tests: ceph-disk: only install multipath on CentOS
- If installed on Ubuntu where multipath does not activate properly, it
interferes with the other tests.
Signed-off-by... - 06:46 AM Revision 182676d6 (ceph): tests: ceph-disk: workunit must fail when test fail
- Signed-off-by: Joe Julian <me@joejulian.name>
- 06:46 AM Revision b86d9fd9 (ceph): ceph-disk: ensure ceph owner on udev change
- On udev change the owner of the device switch back to the default. If
that happens on a journal while an OSD is being... - 06:46 AM Revision cc13fa05 (ceph): ceph-disk: fix typos in udev rules
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 06:46 AM Revision f0a47578 (ceph): ceph-disk: systemd must not kill a running ceph-disk
- When activating a device, ceph-disk trigger restarts the ceph-disk
systemd service. Two consecutive udev add on the s... - 06:46 AM Revision d521a750 (ceph): ceph-disk: upstart must not run ceph-disk activate concurrently
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 06:46 AM Revision 17c60457 (ceph): ceph-disk: a journal partition may survive a data partition
- When a data partition is removed and the journal partition is not
removed, ceph-disk list will not find a journal_for... - 06:46 AM Revision 6ca6653d (ceph): ceph-disk: - is translated into / with systemd
- When running ceph-disk trigger /dev/dm-1 with systemd, the path name is
translated into /dev/dm/1 because of systemd ... - 06:46 AM Revision 3d0e7ca6 (ceph): ceph-disk: make ceph-disk list /dev/vdb equivalent to list vdb
- The ceph-disk list argument must be the device name without the leading
/dev/. This is error prone and silently does ... - 06:46 AM Revision 9e796dc8 (ceph): ceph-disk: prefer sgdisk to blkid to retrieve partition UUID
- blkid 2.23.2 which is the default for official CentOS 7 cloud images
fails on journal device. It would be better to u... - 06:46 AM Revision 5aeca731 (ceph): ceph-disk: support --verbose with --log-stdout
- Set the LOG level as well as the channel level, otherwise the debug
messages are trimmed before they reach the channe... - 06:46 AM Revision ad2d46ce (ceph): ceph-disk: do not hide ceph-disk prepare stack trace
- raise without an argument so the original stack trace is shown when
ceph-disk prepare fails.
Signed-off-by: Loic Dac... - 06:46 AM Revision e2c553ee (ceph): ceph-disk: guard partprobe with udevadm settle
- Call udevadm settle before and after partprobe.
A side effect of partprobe is to remove partitions and add them agai... - 06:46 AM Revision 0dd23649 (ceph): ceph-disk: move update_partition from main_prepare to prepare_dev
- The update_partition call in main_prepare happens immediately after
prepare_dev but only if the data argument is a bl... - 06:07 AM Backport #13195 (Resolved): should recalc the min_last_epoch_clean when decode PGMap
- https://github.com/ceph/ceph/pull/6154
- 06:07 AM Bug #13112: should recalc the min_last_epoch_clean when decode PGMap
- master still is == infernalis
- 01:09 AM Bug #13112 (Pending Backport): should recalc the min_last_epoch_clean when decode PGMap
- 05:19 AM Revision de9149d7 (ceph): Merge pull request #5976 from yuyuyu101/wip-fix-metadata-conf
- Librbd: Fix incorrect metadata filter behavior
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:52 AM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- Looks great! Personally I find the cython more readable too.
I'm not worried about older librbd versions. When thi... - 02:40 AM CephFS Bug #12674: Semi-reproducible crash of ceph-fuse
- It's likely been fixed by pull request https://github.com/ceph/ceph/pull/4753 (it's large change, we haven't back-por...
- 02:30 AM CephFS Support #13055: Problem with disconnect fuse by mds
- It's likely been fixed by pull request https://github.com/ceph/ceph/pull/4753. could you try compiling ceph-fuse from...
09/21/2015
- 11:25 PM Bug #13185: osd/ReplicatedPG.cc: 11062: FAILED assert(obc) on hammer -> infernalis upgrade
- 01:11 AM Bug #13185 (Resolved): osd/ReplicatedPG.cc: 11062: FAILED assert(obc) on hammer -> infernalis upg...
- ...
- 11:14 PM CephFS Feature #12204 (Resolved): ceph-fuse: warn and shut down when there is no MDS present
- https://github.com/ceph/ceph/pull/5416
Thanks Yuan Zhou! - 11:13 PM Revision 19a480b7 (ceph): Merge pull request #5750 from wonzhq/rbd-write-full
- librbd: do write_full for whole object write
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Reviewed-by: Josh Dur... - 11:13 PM CephFS Bug #12971 (Resolved): TestQuotaFull fails
- https://github.com/ceph/ceph/pull/5942
- 11:10 PM CephFS Bug #11835 (Resolved): FuseMount.umount_wait can hang
- 11:09 PM Revision e3c99476 (ceph): Merge pull request #453 from ceph/wip-11835
- tasks/cephfs: time out on ceph-fuses that don't die
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 11:05 PM Revision eab70197 (ceph): tasks/ceph: wait for MDS to be active when creating a cluster
- This is the correct implementation of 685d76a77ca16ca601a99148ef507cfde1fb3593,
merged while broken in ff1655cb57793f... - 11:02 PM Revision ac2953a4 (ceph): Merge pull request #5416 from zhouyuan/ceph_fuse_12204
- ceph-fuse: warn and shut down when there is no MDS present
Reviewed-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Gr... - 11:01 PM Bug #13032 (Fix Under Review): client nonce collision due to unshared pid namespaces
- https://github.com/ceph/ceph/pull/6022
- 10:57 PM Revision 42c657a6 (ceph): Merge pull request #5826 from ukernel/wip-osx-port
- fix compilation on OSX/FreeBSD
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:56 PM Revision a3a8c85b (ceph): use simplifed messenger constructor for clients
- This is all mechanical except the calculation of the nonce, which is
now always randomized for clients.
Fixes: #1303... - 10:56 PM Revision e3785b0b (ceph): msg: add simplified messenger constructor
- Several callers create messengers using exactly the same parameters:
- reading the ms type from cct that is also pas... - 10:55 PM Revision fe54bd1b (ceph): Merge branch 'wip-12971' of git://github.com/jcsp/ceph
- Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Conflicts:
src/osdc/Objecter.cc
Signed-off-by: Greg Farnum <gfarnum@... - 10:52 PM Revision 2c5dcd34 (ceph): Merge pull request #5644 from majianpeng/mds-support-iohint
- Mds journal support iohint
Reviewed-by: John Spray <john.spray@redhat.com> - 10:51 PM CephFS Bug #12506 (Resolved): "Fuse mount failed to populate" error
- 10:50 PM Revision 76e2e627 (ceph): Merge pull request #5966 from ukernel/wip-12506
- Wip 12506
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:49 PM Revision cb7786b1 (ceph): Merge pull request #5962 from majianpeng/client-fix
- Client fix mini bugs.
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:46 PM Revision 66a9bfdb (ceph): osd/: remove unused pg_hit_set_history_t::current_last_stamp
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 09:50 PM Bug #13000: ceph-disk failure to activate with dmcrypt
- ceph-deploy still fails with the same symptoms
- 10:02 AM Bug #13000: ceph-disk failure to activate with dmcrypt
- ...
- 09:28 PM Bug #13108 (Resolved): pg stat mismatch caused by double evict on same object
- 09:20 PM Bug #13158 (Rejected): hammer -> infernalis upgrade tests fail with hit_set_trim assert (timezones!)
- no, it's not timezones. see #13185
- 09:18 PM CephFS Bug #13167: mds: replay gets stuck (on out-of-order journal replies?)
- We should be detecting holes in the journal and shutting down with a nice message or clear assert or something instea...
- 12:59 PM CephFS Bug #13167 (Duplicate): mds: replay gets stuck (on out-of-order journal replies?)
- Write_pos of journal seems to be pointing to somewhere in object 200.00000002, But size of object 200.00000001 is 313...
- 09:17 PM Bug #11512 (Need More Info): "FAILED assert(0 == "unexpected error")" in upgrade:giant-x-hammer-d...
- 09:17 PM Bug #11512: "FAILED assert(0 == "unexpected error")" in upgrade:giant-x-hammer-distro-basic-vps run
- Jeff Epstein wrote:
> We believe that this crash is a result of ceph-osd running out of file descriptors, which stem... - 09:11 PM Bug #13194 (Resolved): can't find python-flask during upgrade
- reliably hitting this with hammer-x test,
description: upgrade:hammer-x/stress-split-erasure-code-x86_64/{0-tz-eas... - 09:04 PM Revision 30332e3c (ceph): mon/PaxosService: include msg and con ptr in dispatch debug
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:32 PM Stable releases Tasks #11644: firefly v0.80.11
- #12942 needs to go into 0.80.11 so we will need another integration round
- 08:31 PM CephFS Feature #13193 (Duplicate): qa: test behavior on cache pools
- 06:48 PM CephFS Feature #13193 (Duplicate): qa: test behavior on cache pools
- We don't run the FS on any cache pools right now. We should start doing so on an appropriate assortment (TBD). Probab...
- 08:07 PM Revision ee818120 (ceph): Merge pull request #5234 from SUSE/wip-12244-firefly
- Civetweb RGW appears to report full size of object as downloaded when only partially downloaded
- 07:35 PM Revision bb8b422b (ceph): Merge pull request #4535 from xinxinsh/wip-11416-firefly
- rgw: use correct objv_tracker for bucket instance
- 07:30 PM rbd Feature #12901 (In Progress): librbd: zone + zonegroup configuration
- 07:14 PM Revision 930d8eb1 (ceph): PG: ignore info from down osd
- Fixes: #12990
Backport: firefly, hammer
Signed-off-by: Samuel Just <sjust@redhat.com> - 07:08 PM Revision 4b003508 (ceph): OSDMap.h: add has_been_up_since
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 06:51 PM Revision e664547c (ceph): Merge pull request #6014 from athanatos/wip-13108
- Revert "osd: purge the object from the cache when proxying and not pr…
Reviewed-by: Sage Weil <sage@redhat.com> - 06:51 PM Revision 4e7fb86e (ceph): Merge pull request #6015 from athanatos/wip-13143
- osd/: find_object_context: return obc for head for snapdir if non null
Reviewed-by: Sage Weil <sage@redhat.com> - 06:46 PM Revision 6f2c2aa6 (ceph): Merge pull request #6017 from athanatos/wip-13150
- ReplicatedPG::get_snapset_context: set exists to false for new ssc wi…
Reviewed-by: Sage Weil <sage@redhat.com> - 06:43 PM Revision 0bfefdf5 (ceph): Merge pull request #6013 from athanatos/wip-12828
- Wip 12828
Reviewed-by: Sage Weil <sage@redhat.com> - 06:36 PM Revision c27b73f9 (ceph): mon/OSDMonitor: respect NODOWN on osd failure checks
- Backport: hammer, firefly
Signed-off-by: Sage Weil <sage@redhat.com> - 06:35 PM Revision ea977611 (ceph): systemd: increase nproc ulimit
- We were observed to be hitting the limit on centos7
(triggering pthread_create failures) on a ~2000 OSD cluster.
Inc... - 06:35 PM Revision 9f89ae7c (ceph): mon/PGMonitor: avoid useless register_new_pgs work
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:34 PM Revision 2a01bbc4 (ceph): mon: make all paxos-related timeouts relative to mon_lease
- It is a pain to adjust these settings for slow/loady clusters.
Instead, make everything a ratio of mon_lease (still d... - 06:16 PM Bug #13192 (Resolved): stuck recovering, unfound hit set due to removing it while !active
- ubuntu@teuthology:/a/samuelj-2015-09-18_22:24:48-rados-wip-sam-testing-distro-basic-multi/1062995/remote
Related: ... - 06:01 PM Revision 6d82eb16 (ceph): mon: handle case where mon_globalid_prealloc > max_global_id
- This triggers with the new larger mon_globalid_prealloc value. It didn't
trigger on the existing cluster I tested on... - 06:01 PM Revision f545a0f4 (ceph): mon: change mon_globalid_prealloc to 10000 (from 100)
- 100 ids (session 100 authentications) can be consumed quite quickly if
the monitor is being queried by the CLI via sc... - 05:49 PM Revision 5e2c6655 (ceph): scripts: release_notes can track original issue
- ceph_release_notes helper now has `--original-issue` (default) and
`--no-original-issue` flags added. This is useful
... - 03:41 PM Bug #13190 (Fix Under Review): osd/ReplicatedPG.cc: 7247: FAILED assert(agent_state)
- https://github.com/ceph/ceph/pull/6008
- 12:22 PM Bug #13190 (Resolved): osd/ReplicatedPG.cc: 7247: FAILED assert(agent_state)
- ...
- 03:41 PM Revision fd9ce66e (ceph): osd/ReplicatedPG: tolerate promotion completion with stopped agent
- We may start a promotion, then get a pool update that disables the
agent, and then complete it. We should not segfau... - 03:35 PM Revision 7bb316fb (ceph): Merge pull request #5918 from oritwas/wip-5378
- rgw: make radosgw-admin user rm idempotent
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 03:33 PM Bug #13155 (Duplicate): ceph-disk: permission denied if udev races with mkfs
- 03:23 PM rgw Bug #12780 (Pending Backport): rgw: segments are read during HEAD on Swift DLO
- 03:22 PM Revision 63be2797 (ceph): Merge pull request #5996 from rzarzynski/wip-12780
- rgw: don't read actual data on user manifest HEAD
- 03:20 PM Revision 17b68616 (ceph): Merge pull request #5974 from Sandy4999/wip-rgw-errmsg
- rgw: add a new error message for user conflict when using Admin Ops API
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 02:23 PM Bug #12748: bug with cache/tiering and snapshot reads [merged, needs a test in ceph-qa-suite]
- Won't make progress on this in the next few days, unassigning myself for now.
- 01:48 PM Bug #12936 (Fix Under Review): shec fails i386 make check
- https://github.com/ceph/ceph/pull/6006
- 01:43 PM Bug #12936: shec fails i386 make check
- With non optimized code on i386 (or on amd64):...
- 01:41 PM Bug #12936: shec fails i386 make check
- * valgrind is happy
* the bug disapear when adding print statements in some places
* the bug disapear when the code... - 12:06 PM Bug #12936: shec fails i386 make check
- Fail for 6/3/2 and 9/4/2 only
- 09:28 AM Bug #12936 (In Progress): shec fails i386 make check
- 01:44 PM CephFS Bug #12674: Semi-reproducible crash of ceph-fuse
- Please also note that this crash can be triggered with a simple operation of the style
> find . -name \*.txt | xa... - 01:20 PM CephFS Bug #12674: Semi-reproducible crash of ceph-fuse
- RP https://github.com/ceph/ceph/pull/4753 may fix this issue. could you try compiling ceph-fuse from the newest ceph ...
- 11:10 AM CephFS Bug #12674: Semi-reproducible crash of ceph-fuse
- > Status changed from New to Need More Info
What kind of info are you looking for? As I've just hit another situat... - 01:32 PM CephFS Bug #13166: MDS: standby-replay does not change client_incarnation properly
- 07:44 AM CephFS Bug #13166 (Fix Under Review): MDS: standby-replay does not change client_incarnation properly
- https://github.com/ceph/ceph/pull/6003
- 01:25 PM CephFS Support #13055: Problem with disconnect fuse by mds
- attached last logs.
last error msg is different from previous, so maybe i should attach other when they happen? - 01:16 PM CephFS Support #13055: Problem with disconnect fuse by mds
- I can't open the issue neither. But this seems to be duplicate of #12674
- 01:08 PM CephFS Support #13055: Problem with disconnect fuse by mds
- We use clients with kernel version 3.13.0 (current client host which got that error have 3.13.0-58-generic, others ha...
- 03:05 AM CephFS Support #13055: Problem with disconnect fuse by mds
- We never saw this backtrace before. Which version of kernel are you using? Please apply the attached debug patch to t...
- 01:15 PM rbd Bug #13164: librbd: reads larger than cache size hang
- "ObjectCacher::_readx" has logic to ensure that it won't flood the cache with concurrent reads, but it doesn't handle...
- 10:45 AM rbd Bug #13164: librbd: reads larger than cache size hang
- is this bug complex?i want to fix this bug,This process will deepen my understanding of CEPH.
- 12:17 PM Revision 1a0f68e0 (ceph): upgrade/hammer-x/point-to-point: upgrade client for final test
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:16 PM Revision eebd63a7 (ceph): upgrade/hammer-x/point-to-point: use proper hammer test.sh
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:17 AM Revision e8cce089 (ceph): bug fix: osd: requeue_scrub when kick_object_context_blocked
- when read miss in writeback cache pool, osd do_proxy_read first
and maybe promote it. but in this case, the op is not... - 10:59 AM Linux kernel client Bug #13189 (Closed): Reboot systerm can not set up.
- My system kernal is 3.10
The operation is below:
[root@client101 ~]# rbd map c1
/dev/rbd1
[root@client101 ~]#... - 10:01 AM RADOS Feature #13188: use crushtool to simulate real pg distribution for a specific pool
- https://github.com/ceph/ceph/pull/6004
- 10:00 AM RADOS Feature #13188 (New): use crushtool to simulate real pg distribution for a specific pool
- We had re-weighted our cluster to make pg evenly-distribution at the time we built up this cluster, but pg becomes un...
- 09:25 AM Revision 07aa4480 (ceph): Merge pull request #6003 from ukernel/wip-13166
- Wip 13166
Reviewed-by: John Spray <john.spray@redhat.com> - 07:49 AM Bug #13182 (Resolved): tests.sh fail crushmap validation
- 07:45 AM rbd Feature #13186 (Resolved): I hope retain snapshot of the rbd block, after rbd block export and im...
- (1)I have a rbd block foo_c01,that contain a snapshot foo_c01_s01.then,I export foo_c01 to foo_c01_local.
rbd -p... - 07:42 AM Revision e65fb1ba (ceph): mds: adjust MDSRank::incarnation according to mdsmap
- When a standby-replay MDS replace failed MDS, we need update its
incarnation.
Fixes: #13166
Signed-off-by: Yan, Zhen... - 07:37 AM Bug #13136 (Resolved): install-deps.sh fails on Ubuntu 14.04
- 07:34 AM Revision 8ee93d5f (ceph): PG::handle_advance_map: on_pool_change after handling the map change
- Otherwise, the is_active() checks in the hitset code can erroneously
return true firing off repops stamped with the n... - 07:08 AM Bug #12100: OSD crash, uexpected aio error in FileJournal.cc
- That is everything that kern.log logged that day.
- 06:53 AM Revision 1ec9b658 (ceph): Merge remote-tracking branch 'upstream/master'
- 06:12 AM Revision d6b30dea (ceph): osd/ReplicatedPG: If object exist and not whiteout, don't do touch for
- create.
Also, if object is whiteout, it need transaction op to update xattr
which chanage whiteout to no-whiteout. F... - 06:08 AM Revision 10235e3f (ceph): osd: refactor setting write_fadvise_dontneed pool flag
- Handle together with other flags.
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 06:08 AM Revision b97ae766 (ceph): osd: make 'ceph osd pool get' work for all settable pool flags
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 06:08 AM Revision 48db7b16 (ceph): osd: new pool flags: noscrub, nodeep-scrub
- This allows to disable periodic scrub on per pool basis.
Fixes: #13076
Signed-off-by: Mykola Golub <mgolub@mirantis.... - 06:08 AM Revision 30810da4 (ceph): osd: new pool settings: scrub intervals
- ceph osd pool set $POOL scrub_min_interval N
ceph osd pool set $POOL scrub_max_interval N
ceph osd pool set $POOL d... - 02:05 AM Revision b41f5746 (ceph): Fix unneccessary at/near max target warn in ceph -s when using ecpool
- When calculated objects needing eviction, we use object - hitset_achieve. So setting max objects = 30000, ceph -s wil...
- 01:21 AM Revision daf4f520 (ceph): upgrade/hammer-x/parallel: upgrade client before final workload test
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:14 AM Revision 09318894 (ceph): upgrade/hammer-x: fix full_sequential indentation
- Broken by caa92358572c2a226976adc6488542b409d1b484
Signed-off-by: Sage Weil <sage@redhat.com> - 12:57 AM Revision c4b2d12a (ceph): Merge pull request #6001 from dachary/wip-13182-crushtool
- tests: update to match crushmap validation message
09/20/2015
- 10:13 PM Revision 21a1e75d (ceph): tests: update to match crushmap validation message
- http://tracker.ceph.com/issues/13182 Fixes: #13182
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 09:58 PM Documentation #13183 (Closed): docs.ceph.com leads to nginx welcome page
- When I point browser to docs.ceph.com, I get a page that says "Welcome to nginx! If you see this page, the nginx web ...
- 09:46 PM Bug #13182 (Fix Under Review): tests.sh fail crushmap validation
- 09:41 PM Bug #13182 (In Progress): tests.sh fail crushmap validation
- 08:55 PM Bug #13182: tests.sh fail crushmap validation
- Introduced by https://github.com/ceph/ceph/pull/5979
- 08:53 PM Bug #13182: tests.sh fail crushmap validation
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/7877/console
- 08:51 PM Bug #13182 (Resolved): tests.sh fail crushmap validation
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/7876/console...
- 08:48 PM Bug #13181 (Rejected): crushmap validation timesout on test.sh
- 08:35 PM Bug #13181 (Rejected): crushmap validation timesout on test.sh
- When a crushmap is imported, the validation may timeout if there are too many crush ruleset, because the validation i...
- 06:02 PM Revision 937e4f88 (ceph): rhel 5.9 librados fix, removed blkid from compilation, Fixes #13177
- 05:57 PM CephFS Backport #12097 (In Progress): kernel_untar_build fails on EL7
- 05:56 PM Revision 01dc221f (ceph): qa: update to newer Linux tarball
- This should make newer gcc releases happier in their default configuration.
kernel.org is now distributing tarballs a... - 05:54 PM Revision 5e8299f0 (ceph): Merge remote-tracking branch 'gh/infernalis'
- 05:50 PM Revision 782855e7 (ceph): Merge pull request #5979 from ceph/wip-crushtest
- mon: fix crush testing for new pools
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:49 PM Revision b4140830 (ceph): Merge pull request #5950 from tchaikov/wip-13112-infernalis
- mon/PGMap: calc min_last_epoch_clean when decode
Reviewed-by: Sage Weil <sage@redhat.com> - 04:15 PM Bug #13180 (Fix Under Review): ceph-disk: --verbose --log-stdout trims --verbose
- https://github.com/ceph/ceph/pull/5999
- 12:23 PM Bug #13180 (Resolved): ceph-disk: --verbose --log-stdout trims --verbose
- The --log-stdout option does not set the log level on the logging channel created. As a result the debug messages are...
- 04:15 PM Bug #13174 (Fix Under Review): ceph-disk: trigger /dev/dm-1 gets /dev/dm/1 instead
- https://github.com/ceph/ceph/pull/5999
- 04:15 PM Bug #13160 (Fix Under Review): ceph-disk: duplicate osd mount points
- https://github.com/ceph/ceph/pull/5999
- 04:15 PM Bug #13157 (Fix Under Review): ceph-disk: list fails on isolated journals
- https://github.com/ceph/ceph/pull/5999
- 04:15 PM Fix #13154 (Fix Under Review): ceph-disk: list /dev/vdb does not filter as expected
- https://github.com/ceph/ceph/pull/5999
- 04:14 PM Bug #13153 (Fix Under Review): ceph-disk: blkid 2.23.2 fails on journal device on CentOS 7
- https://github.com/ceph/ceph/pull/5999
- 04:14 PM Bug #13000 (Fix Under Review): ceph-disk failure to activate with dmcrypt
- https://github.com/ceph/ceph/pull/5999
- 04:14 PM Bug #12787 (Fix Under Review): ceph-disk does not activate with systemd on some CentOS 7
- https://github.com/ceph/ceph/pull/5999
- 03:12 PM Revision 642cbd88 (ceph): Merge pull request #5998 from dachary/wip-13136-python3-coverage
- install-deps: enable python3
- 12:16 PM Bug #11512: "FAILED assert(0 == "unexpected error")" in upgrade:giant-x-hammer-distro-basic-vps run
- We believe that this crash is a result of ceph-osd running out of file descriptors, which stems from running it direc...
- 07:59 AM Bug #11512 (Fix Under Review): "FAILED assert(0 == "unexpected error")" in upgrade:giant-x-hammer...
- 12:09 PM Cleanup #13179 (New): ceph-disk: use systemd-escape instead of hardcoded translation
- When http://www.freedesktop.org/software/systemd/man/systemd-escape.html is available on all supported distributions,...
- 11:20 AM Bug #13136 (Fix Under Review): install-deps.sh fails on Ubuntu 14.04
- https://github.com/ceph/ceph/pull/5998
- 11:18 AM Revision 4da6793d (ceph): install-deps: enable python3
- The upstream regression has been fixed, we can re-enable python3
support.
http://tracker.ceph.com/issues/13136 Fixes... - 10:24 AM Stable releases Tasks #13097 (Closed): replicatedPG:the assert occurs in the fuction ReplicatedPG::on_local_recover.
- 07:48 AM rgw Bug #10701: rgw: content length parsing calls strtol() instead of strtoll()
- Firefly backport staged at: http://tracker.ceph.com/issues/13178
- 07:09 AM rgw Bug #10701: rgw: content length parsing calls strtol() instead of strtoll()
- Thanks, Robin. Good catch!
- 07:46 AM rgw Backport #13178 (In Progress): rgw: content length parsing calls strtol() instead of strtoll()
- 07:10 AM rgw Backport #13178 (Resolved): rgw: content length parsing calls strtol() instead of strtoll()
- https://github.com/ceph/ceph/pull/5997
- 07:45 AM Revision 86f9e55f (ceph): rgw: use strict_strtoll() for content length
- instead of strict_strtol().
Backport: giant, firefly
Fixes: #10701
Reported-by: Axel Dunkel <ad@dunkel.de>
Signed-o... - 04:30 AM Bug #13177: rhel 5.9 doesn't compile (librados only) due to blkid error
- Actually, configure.ac is probably fine, but a requires Makefile.am check to exclude blkid for librados only compile ...
- 04:24 AM Bug #13177 (Closed): rhel 5.9 doesn't compile (librados only) due to blkid error
- Changes introduced in configure.ac check for blkid functions which don't exist on rhel 5.9. off master the configure ...
- 12:11 AM Bug #13176: test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::Lock(bool)
- David, does that ring a bell ? I'm setting it as Urgent because it create noises in make check (happened twice in the...
- 12:10 AM Bug #13176 (Resolved): test/ceph_objectstore_tool.py: common/Mutex.cc: In function 'void Mutex::L...
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/7811/console...
09/19/2015
- 10:39 PM rgw Documentation #12568 (New): update Install Ceph Object Gateway documentation to reflect Civetweb
- 09:12 PM rgw Documentation #12568 (In Progress): update Install Ceph Object Gateway documentation to reflect C...
- Oops - edited the wrong issue by mistake.
- 09:34 PM rgw Bug #12978: rgw: init_rados failed leads to repeated delete
- Not backportable to firefly (the code being fixed does not exist there).
- 09:33 PM rgw Backport #13051 (Rejected): rgw: init_rados failed leads to repeated delete
- The code this is fixing does not exist in firefly.
- 09:21 PM Revision f7eb1d8c (ceph): Merge pull request #5994 from SUSE/wip-13175
- doc: do not promise backports to Dumpling
Reviewed-by: Sage Weil <sage@redhat.com> - 09:20 PM rgw Backport #13048 (In Progress): Content-Type header should have correct initial capitals
- 09:14 PM Bug #13175 (In Progress): Documentation promises backports to EOL release (Dumpling)
- Master PR: https://github.com/ceph/ceph/pull/5994
- 08:22 PM Bug #13175 (Resolved): Documentation promises backports to EOL release (Dumpling)
- As of May 2015 we are no longer backporting anything to Dumpling. However, the documentation does not reflect this:
... - 08:30 PM Revision 170f9add (ceph): doc: do not promise backports to Dumpling
- Dumpling was retired in May 2015.
http://tracker.ceph.com/issues/13175 Fixes: #13175
Signed-off-by: Nathan Cutler <... - 08:17 PM Backport #13169 (In Progress): update docs to point to download.ceph.com
- 08:15 PM Backport #13169 (New): update docs to point to download.ceph.com
- 08:13 PM Backport #13169 (In Progress): update docs to point to download.ceph.com
- 03:51 AM Backport #13169 (Resolved): update docs to point to download.ceph.com
- https://github.com/ceph/ceph/pull/5993
- 08:12 PM Revision f71a6ebf (ceph): doc: correct links to download.ceph.com
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
(cherry picked from commit 387d7800359154950431d0984c756f43f21dd9b4)
... - 07:51 PM devops Backport #13168 (In Progress): upstart: configuration is too generous on restarts
- 03:52 AM devops Backport #13168 (New): upstart: configuration is too generous on restarts
- 03:50 AM devops Backport #13168 (Resolved): upstart: configuration is too generous on restarts
- https://github.com/ceph/ceph/pull/5992
- 07:50 PM Revision 20ad17d2 (ceph): upstart: limit respawn to 3 in 30 mins (instead of 5 in 30s)
- It may take tens of seconds to restart each time, so 5 in 30s does not stop
the crash on startup respawn loop in many... - 07:48 PM rgw Bug #10701 (Pending Backport): rgw: content length parsing calls strtol() instead of strtoll()
- This was marked for backport to firefly, but it's NOT in the main github.com/ceph/ceph firefly branch as of 2015/09/1...
- 06:57 PM Backport #13043 (In Progress): ThreadPool add/remove work queue methods not thread safe
- 06:56 PM Revision 8c14cad0 (ceph): WorkQueue: add/remove_work_queue methods now thread safe
- These methods were not acquiring the ThreadPool lock when
manipulating the work_queue collection. This was causing
o... - 02:04 PM Bug #13127 (Fix Under Review): ObjectCacher: coalesce multiple writes to a single object into one IO
- https://github.com/ceph/ceph/pull/5990
- 11:03 AM Revision 210156f3 (ceph): Merge pull request #5965 from jcsp/wip-get-or-create-output
- mon: fix auth get-or-create output
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:09 AM Bug #13174: ceph-disk: trigger /dev/dm-1 gets /dev/dm/1 instead
- http://www.freedesktop.org/software/systemd/man/systemd-escape.html is necessary to avoid that kind of problem (/ are...
- 09:44 AM Bug #13174 (Resolved): ceph-disk: trigger /dev/dm-1 gets /dev/dm/1 instead
- ...
- 08:40 AM Bug #13160: ceph-disk: duplicate osd mount points
- With the current approach, the latest we cover all cases, at the expense of running activate for each and every udev ...
- 12:16 AM Bug #13160: ceph-disk: duplicate osd mount points
- I think it would be better to move flock outside of the systemd service in the udev action with the -n option. This w...
- 08:24 AM devops Backport #13172 (New): rbd-replay* should ship in ceph-common
- 08:22 AM devops Backport #13172 (Resolved): rbd-replay* should ship in ceph-common
- https://github.com/ceph/ceph/pull/5790
- 08:20 AM Backport #13171 (New): objecter: cancellation bugs
- 08:20 AM Backport #13171 (Resolved): objecter: cancellation bugs
- https://github.com/ceph/ceph/pull/6155
- 07:09 AM Bug #11512: "FAILED assert(0 == "unexpected error")" in upgrade:giant-x-hammer-distro-basic-vps run
- This bug also affects me. ceph-osd crashes every few hours with this. Enclosed please find the logs.
- 04:59 AM Backport #13041 (In Progress): common/Thread:pthread_attr_destroy(thread_attr) when done with it
- 04:47 AM Backport #12488 (In Progress): pg_interval_t::check_new_interval - for ec pool, should not rely o...
- 04:45 AM Backport #13038 (In Progress): hit set clear repops fired in same epoch as map change -- segfault...
- 04:42 AM Revision 48c929e6 (ceph): PG::handle_advance_map: on_pool_change after handling the map change
- Otherwise, the is_active() checks in the hitset code can erroneously
return true firing off repops stamped with the n... - 04:01 AM Bug #11602 (Resolved): crush: take crashes due to invalid arg
- 04:00 AM Backport #11741 (Resolved): crush: take crashes due to invalid arg
- 03:59 AM Bug #11762 (Resolved): Memory leak in Mutex.cc, pthread_mutexattr_init without pthread_mutexattr_...
- 03:58 AM Backport #12393 (Resolved): Memory leak in Mutex.cc, pthread_mutexattr_init without pthread_mutex...
- 03:57 AM Backport #12484 (In Progress): mon: MonitorDBStore iterator's get_next_key() returns wrong keys
- 03:56 AM Bug #11470 (Resolved): mon: leaked Messenger, MLog on shutdown
- 03:56 AM Backport #12485 (Resolved): mon: leaked Messenger, MLog on shutdown
- 03:52 AM Backport #13170 (Resolved): update docs to point to download.ceph.com
- https://github.com/ceph/ceph/pull/6156
- 12:07 AM CephFS Bug #13167 (Resolved): mds: replay gets stuck (on out-of-order journal replies?)
- ubuntu-2015-09-17_16:55:52-fs-greg-fs-testing---basic-multi/1061690/ceph-mds.a.log
This MDS went in and out of rep... - 12:04 AM CephFS Bug #13166: MDS: standby-replay does not change client_incarnation properly
- If we need more logs, I copied the standby MDS log to ubuntu-2015-09-17_16:55:52-fs-greg-fs-testing---basic-multi/106...
09/18/2015
- 11:52 PM CephFS Bug #13166: MDS: standby-replay does not change client_incarnation properly
- Obvious fix is to have MDSRank check the incarnation and update, but I want us to look more deeply at how the replayi...
- 11:24 PM CephFS Bug #13166: MDS: standby-replay does not change client_incarnation properly
- Hmm, I don't think we should actually be doing operations as mds.0.0 when we're a standby for the real mds.0.0 either...
- 11:22 PM CephFS Bug #13166: MDS: standby-replay does not change client_incarnation properly
- 10:59 PM CephFS Bug #13166 (Resolved): MDS: standby-replay does not change client_incarnation properly
- ...
- 11:44 PM Bug #13160: ceph-disk: duplicate osd mount points
- ...
- 11:00 PM Bug #13160: ceph-disk: duplicate osd mount points
- The ceph-activate that was run via systemctl is interrupted before it can finish and that leaves the file system moun...
- 10:37 PM Bug #13160 (In Progress): ceph-disk: duplicate osd mount points
- 03:46 PM Bug #13160 (Won't Fix): ceph-disk: duplicate osd mount points
- The scenario creating duplicate mount points is when the the osd is destroyed while activating. This is a border case...
- 03:25 PM Bug #13160: ceph-disk: duplicate osd mount points
- It probably is a leftover of ...
- 02:38 PM Bug #13160 (Resolved): ceph-disk: duplicate osd mount points
- * ceph-disk prepare /dev/vdb
* ceph-disk list... - 11:25 PM rbd Bug #13122: rbd: stripingv2 feature bit not set when unnecessary for striping params
- Like Ilya mentioned on ceph-users (http://permalink.gmane.org/gmane.comp.file-systems.ceph.user/23841), this is was i...
- 10:26 PM rgw Bug #13165 (Won't Fix): rgw: return 409 for conflict
- If there are two requests racing for the same object (PUT), one get through and another one failed, currently both re...
- 10:14 PM rbd Bug #13124: librbd order limits inconsistent with rbd cli
- There are a few things going on here.
1) librbd is enforcing limits on order, they're just higher than /usr/bin/rb... - 10:13 PM rbd Bug #13164 (Resolved): librbd: reads larger than cache size hang
- This can be triggered by using an image with order 26 (so objects are 64MB, larger than the default cache size), and ...
- 09:31 PM Revision f6a96ad8 (ceph): upgrade/hammer-x: use eastern tz for all upgrades
- Hammer doesn't handle mixed timezones and hit_sets (cache pools)
correctly. Avoid it.
Signed-off-by: Sage Weil <sag... - 09:29 PM Revision a27cb8db (ceph): timezone: add eastern, pacific, random timezone snippets
- These need to be early tasks, probably. Random will pick either
eastern or pacific tz randomly.
Signed-off-by: Sage ... - 08:08 PM Feature #13163 (New): Add flag to delete a pool and its cache tier.
- There doesn't seem to be a way to delete a pool with a cache tier without going through a number of time consuming st...
- 06:42 PM Bug #13162 (Pending Backport): update docs to point to download.ceph.com
- 06:38 PM Bug #13162: update docs to point to download.ceph.com
- PR for @master@: https://github.com/ceph/ceph/pull/5984
- 05:39 PM Bug #13162 (In Progress): update docs to point to download.ceph.com
- 05:09 PM Bug #13162: update docs to point to download.ceph.com
- Pull request opened https://github.com/ceph/ceph/pull/5983 for @giant@ branch
- 03:54 PM Bug #13162: update docs to point to download.ceph.com
- I guess it really is download.ceph.com
- 03:29 PM Bug #13162 (Resolved): update docs to point to download.ceph.com
- 06:42 PM Revision 498006b3 (ceph): Merge pull request #5984 from ceph/wip-packages
- Fixes locations from ceph.com to download.ceph.com
(For the record, this is to fix http://tracker.ceph.com/issues/13... - 06:20 PM Revision a6f07e9f (ceph): doc: remove mention of ceph-extra as a requirement
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
- 06:19 PM Revision c0ef84fd (ceph): doc: remove ceph-extras
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
- 06:19 PM Revision 387d7800 (ceph): doc: correct links to download.ceph.com
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
- 05:46 PM Revision c1172cad (ceph): mon: fix auth get-or-create output
- Previously the caps were omitted from the
output: they should be present for this
to fulfil the 'get' part of get-or-... - 05:24 PM Bug #12983: handle_sub_read: Bad hash for 116/b1271c9d:test-rados-api-burnupi34-7183-66/foo/head
- 05:24 PM Revision 1c91a934 (ceph): Merge pull request #5983 from ceph/wip-13162
- remove references to ceph.com repos
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 05:06 PM Revision 4346aff8 (ceph): doc: remove ceph-extras from vm-cloud
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
- 05:06 PM Revision 51bb2086 (ceph): doc: update references to packages.ceph and git.ceph
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
- 05:03 PM Revision 7b2fa67a (ceph): ReplicatedPG::get_snapset_context: set exists to false for new ssc with...
- Otherwise, if we do a proxy_write and don't promote it, the ssc will
stick around with exists = true and cause future... - 04:56 PM Revision 4a8b08d1 (ceph): rgw: don't read actual data on user manifest HEAD
- Fixes: #12780
We unconditionally read all the data, which is not needed
when doing HEAD operation on user manifest ob... - 03:40 PM Revision bf9c0058 (ceph): ceph-osd-prestart.sh: no ceph-disk chown
- chown -R ceph:ceph $1 is easy enough.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:26 PM Revision 3fd609f1 (ceph): upgrade/hammer-x: only ubuntu
- the centos packages don't (git)build
Signed-off-by: Sage Weil <sage@redhat.com> - 03:26 PM Revision eae42708 (ceph): upgrade/hammer: do ubuntu for point to point
- centos packages don't (git)build for these old
releases
Signed-off-by: Sage Weil <sage@redhat.com> - 03:06 PM Bug #13059 (Resolved): rpm upgrade does not fix /var/run/ceph ownership/permissions
- 02:05 PM Bug #13059 (Fix Under Review): rpm upgrade does not fix /var/run/ceph ownership/permissions
- https://github.com/ceph/ceph/pull/5980
- 03:06 PM Revision a484bca6 (ceph): Merge pull request #5980 from liewegas/wip-13059
- ceph.spec: fix up /var/run/ceph
Reviewed-by: Sage Weil <sage@redhat.com> - 03:02 PM Revision e44d1e07 (ceph): ceph.spec.in: Fix up (/var)/run/ceph creation
- Fixes: #13059
Signed-off-by: Boris Ranto <branto@redhat.com> - 02:33 PM Revision 9993a2de (ceph): Merge pull request #572 from dachary/wip-duplicate-centos7
- do not duplicate CentOS 7 runs
- 02:32 PM Revision 4ec586b8 (ceph): Merge pull request #5977 from tchaikov/wip-size_t-monstore-txn
- mon: return size_t from MonitorDBStore::Transaction::size()
Reviewed-by: Joao Eduardo Luis <joao@suse.de> - 02:24 PM Revision 99c62674 (ceph): do not duplicate CentOS 7 runs
- The a-supported-distro.yaml file must be outside of the supported distro
directory otherwise it will have all suites ... - 02:19 PM Revision 65565de5 (ceph): erasure-code: isolate isa plugin arch constraint
- Link the distro directory to the directory containing all supported
distros. Add the x86_64 arch contraint required b... - 02:10 PM Revision caa92358 (ceph): Merge pull request #566 from ceph/wip-s3-branch-fix
- Use old branches as is without 'ceph-' for firefly, hammer etc
- 02:06 PM Revision a6fc7c6e (ceph): upgrade/hammer-x: run rados.py to completion before moving on
- Leave the final workloads alone.. those can run in parallel
with other stuff.
Signed-off-by: Sage Weil <sage@redhat.... - 01:55 PM Bug #13158 (Rejected): hammer -> infernalis upgrade tests fail with hit_set_trim assert (timezones!)
- This causes stress-split failures.
Do we
1. backport the tz fix/feature?
2. disable hitset trimming for the su... - 01:47 PM Bug #13157 (Resolved): ceph-disk: list fails on isolated journals
- When /dev/vdc1 is a journal for which the corresponding data partition has been zapped, ceph-disk list fails with
<p... - 01:42 PM Revision 1b3090d5 (ceph): mon/OSDMonitor: fix crush injection error message
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:41 PM Revision 524b0bdc (ceph): mon/OSDMonitor: only test crush ruleset for the newly created pool
- Otherwise, we test *all* crush rules.. which might be a lot, and
which is a big waste of time and effort.
Signed-off... - 01:40 PM Revision aa238e5e (ceph): crush/CrushTester: allow testing by ruleset
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:15 PM Bug #13155: ceph-disk: permission denied if udev races with mkfs
- There is no sure way to protect against this race. Maybe it should just retry a few times. A workaround is to add a u...
- 01:02 PM Bug #13155: ceph-disk: permission denied if udev races with mkfs
- * udev event add on /dev/vdb1 data partition received
* udev chown root /dev/vdbd1
* ceph udev rule chown /dev/vdb1... - 10:07 AM Bug #13155 (Duplicate): ceph-disk: permission denied if udev races with mkfs
- If the udev add event for the data partition is received before the udev add event for the journal partition, activat...
- 01:02 PM CephFS Support #13055: Problem with disconnect fuse by mds
- here it is:
(gdb) bt
#0??0x00007f9afcad779b in raise (sig=11) at ../nptl/sysdeps/unix/sysv/linux/pt-raise.c:37
#... - 12:50 PM CephFS Support #13055: Problem with disconnect fuse by mds
- coredump file is useless without execute file. could you use gdb to check the coredump file and send backtrace to us ...
- 06:16 AM CephFS Support #13055: Problem with disconnect fuse by mds
- http://148.251.180.58/files/cores/core.ceph-fuse.15542.tar.gz - core dump
attached file-log
- 05:40 AM CephFS Support #13055: Problem with disconnect fuse by mds
- Greetings.
We have the same problem after compiling and merging from git. Still ceph-fuse disconnects. after some ti... - 12:23 PM rbd Bug #13156: import/export do not support snapshots
- My team ask me to add a feature about "export rbd block with snapshoot info", I want to know more about this.
any su... - 12:19 PM rbd Bug #13156 (Won't Fix): import/export do not support snapshots
- (1)I create a rbd block named abc;
rbd create abc --size 10
(2)then I create a snapshoot of abc;
rbd snap... - 10:10 AM Bug #13127 (In Progress): ObjectCacher: coalesce multiple writes to a single object into one IO
- 09:39 AM Fix #13154 (Resolved): ceph-disk: list /dev/vdb does not filter as expected
- ceph-disk list /dev/vdb filters the devices with /dev//dev/vdb and it looks like it does not work. It should be calle...
- 09:20 AM Revision 4f553b0e (ceph): Librbd: Fix incorrect metadata filter behavior
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 09:05 AM Revision 3971274b (ceph): mon: return size_t from MonitorDBStore::Transaction::size()
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 08:42 AM Bug #13153 (Resolved): ceph-disk: blkid 2.23.2 fails on journal device on CentOS 7
- Using http://cloud.centos.org/centos/7/images/CentOS-7-x86_64-GenericCloud-1503.qcow2, ceph-disk list fails to match ...
- 08:20 AM Revision 52bbeb18 (ceph): mds: Make mds can dynamic set optracker via asok.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 08:12 AM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- I spent some time yesterday doing a straightforward conversion of rbd.py to Cython. This keeps the same API and passe...
- 08:08 AM Revision 4aaa123c (ceph): osd: Make osd can dynamic set optracker via asok.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 08:08 AM Revision 01f816a0 (ceph): common/TrackedOp: make Tracker can dynamic control.
- After osd/mds initating, the optracker can't set. For dynamic
control, we can set optracker enable or disable at any ... - 07:34 AM Revision 7fe72a2e (ceph): common/TrackedOp: Should lock ops_history_lock when access shutdown.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 07:26 AM Linux kernel client Bug #12538: An image with a long clone chain blows up kernel stack
- It's on the list, I'll get to it sometime after I'm done with #9779.
Is that really something you care about? What'... - 07:02 AM Linux kernel client Bug #12538: An image with a long clone chain blows up kernel stack
- how is this going?
- 06:44 AM Revision 6a4501b2 (ceph): os/FileStore: s/::close(fd)/VOID_TEMP_FAILURE_RETRY(::close(fd)).
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:44 AM Revision a326bd99 (ceph): osd/ReplicatedPG: Remove the unuseful judgement in get_object_context.
- In this case, attrs always null. So it can remove this judgement.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> - 06:44 AM Revision fd0a384c (ceph): osd/ReplicatedPG: Using Hobject_t::get_head.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:44 AM Revision 26fee819 (ceph): osd/ReplicatedPG: using hobject_t::get_snapdir.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:44 AM Revision 8bfbcf69 (ceph): osd/ReplicatedPG:Optimize judgement when calc crc for read whole object.
- If extent.length == oi.size, this mean read success and read the whole
object. No need other conditions.
Signed-off-... - 06:44 AM Revision bdfb2391 (ceph): osd/ReplicatedPG: Add verify checksum for SPARSE_READ.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:44 AM Revision 0d266941 (ceph): osd/ReplicatedPG: Remove the duplicated code.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:39 AM Revision 75321943 (ceph): osd/ReplicatedPG: for osd_op_create, if ob existed don't do t->touch.
- Although if ob existed, t->touch don't meet error. But this cause one
transaction include write journal.
Signed-off-... - 03:58 AM Revision c1afc385 (ceph): unsigned type is short for journal max_size,use uint64_t instead.
- Signed-off-by: Xie Rui jerry.xr86@gmail.com
- 03:18 AM Revision f25b67fa (ceph): rgw: add a new error message for user conflict when using Admin Ops API
- Add a new error message to indicate user conflict, which was using the error code for bucket conflict.
Signed-off-by... - 02:14 AM Revision fd5ed153 (ceph): Merge pull request #5948 from flyd1005/master
- doc: delete wrong description of installing RPMs
- 01:36 AM CephFS Bug #12506 (In Progress): "Fuse mount failed to populate" error
- https://github.com/ceph/ceph/pull/5966#issuecomment-141302916
09/17/2015
- 11:54 PM Bug #13150 (Resolved): Error: oid 223 read returned error code -2
- 2015-09-16T13:36:53.624 INFO:tasks.rados.rados.0.mira038.stderr:1565: Error: oid 223 read returned error code -2
201... - 11:53 PM Revision 490938e3 (ceph): osd/: find_object_context: return obc for head for snapdir if non null
- The head obc may have an in progress operation holding a lock, we
need to block on the lock for ordering reasons.
Fi... - 10:46 PM Bug #13080: python-rados in PyPI / with python3 ?
- packages for pypi are covered by #5900 - it's a good idea, it simply hasn't been finished yet.
Are there specific ... - 10:35 PM Bug #12509 (Rejected): CEPH_QA_SUITE/AARCH64:Command failed (workunit test rbd/test_librbd_python...
- This is running a version of the librbd python tests (test_rbd.py) from the master branch, which won't work against o...
- 09:57 PM Bug #13136: install-deps.sh fails on Ubuntu 14.04
- Once https://bitbucket.org/pypa/wheel/issues/148/unorderable-types-error-for-python-3 is fixed we can revert https://...
- 08:51 PM Bug #13136 (Resolved): install-deps.sh fails on Ubuntu 14.04
- 07:50 AM Bug #13136: install-deps.sh fails on Ubuntu 14.04
- https://github.com/ceph/ceph/pull/5960
- 07:38 AM Bug #13136 (Fix Under Review): install-deps.sh fails on Ubuntu 14.04
- 07:32 AM Bug #13136 (Resolved): install-deps.sh fails on Ubuntu 14.04
- It fails because pip wheel coverage no longer works with python3
https://bitbucket.org/pypa/wheel/issues/148/unord... - 09:57 PM RADOS Bug #13146 (Resolved): mon: creating a huge pool triggers a mon election
- AFAICS this is just because we do a lot of work creating the pg entries in the table all at once. We could do them i...
- 09:30 PM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- cython looks pretty interesting, with its finer control via sig_[on|off] and 'with [no]gil'.
It sounds like sig_on... - 09:22 PM Bug #13117 (Resolved): msgr creatse a zillion threads
- 09:15 PM Bug #13117: msgr creatse a zillion threads
- Confirmed, the fixes from earlier this week resolved this!
- 08:50 PM Bug #13117: msgr creatse a zillion threads
- pretty sure this is from mon memory leaks:
- mon hits its memory threshold, all client reader threads block
- cli... - 03:15 PM Bug #13117: msgr creatse a zillion threads
- -Enabling debug ms = 10 either minimizes or fixes it. boooooo.-
Update: spoke too soon, triggered it! - 07:09 PM rbd Bug #13082 (Resolved): Valgrind memcheck detects out-of-bounds memory read
- 07:09 PM Revision c3731105 (ceph): Merge pull request #5926 from dillaman/wip-13082
- include/inline_memory: out-of-bounds read on unaligned memory
Reviewed-by: Sage Weil <sage@redhat.com> - 06:51 PM Bug #13134: old leveldb is slow (firefly->hammer upgrade leads to slow requests)
- I just deleted the logs of osd.3, restarted it and tried the "rbd info" again. This time I ran again these commands:
... - 06:43 PM Bug #13134: old leveldb is slow (firefly->hammer upgrade leads to slow requests)
- I deleted the logs of osd.3, restarted it and tried the "rbd info" again. Same as before:...
- 06:39 PM Bug #13134: old leveldb is slow (firefly->hammer upgrade leads to slow requests)
- As discussed with sjusthm I ran the following commands. It's strange, but this time "ceph -w" didn't show any warning...
- 08:34 AM Bug #13134: old leveldb is slow (firefly->hammer upgrade leads to slow requests)
- It seems I found a way to reliably reproduce blocked requests. A simple "rbd info" on this image *always* takes aroun...
- 06:58 AM Bug #13134 (Closed): old leveldb is slow (firefly->hammer upgrade leads to slow requests)
- Yesterday I upgraded a firefly cluster (started with argonaut several years ago) to hammer 0.94.3. The cluster was co...
- 05:56 PM Bug #13143: incorrect buffer at pos 517268
- Only saw this once reverting the patch causing 13108, not sure why yet.
- 05:56 PM Bug #13143 (Resolved): incorrect buffer at pos 517268
- ubuntu@teuthology:/a/samuelj-2015-09-16_10:11:10-rados-wip-sam-testing-distro-basic-multi/1060190/remote
- 05:37 PM Bug #8907 (Duplicate): All user traffics will start to get 500 after some time if (m+1) OSDs of o...
- Dup to 12623
- 05:33 PM Bug #12581 (Can't reproduce): osd: pg stuck at peering
- We haven't seen this since last time talking with Sam, close this issue.
- 05:12 PM Feature #13142 (Resolved): osd: warning if pg has not been scrubbed for a long time
- For large clusters with aggressive throttling on scrubbing, scrubbing might take forever and thus some PG might not b...
- 05:11 PM Bug #13109: msg/async leak, observed on mon
- Hi sage, after detail inspects, I don't find any clue about async leak. And I don't get your point about async cause ...
- 05:11 PM Bug #13119: msg/async: does not wake up from standby?
- Eh, ignore my last comment. It got lost ....
- 07:36 AM Bug #13119: msg/async: does not wake up from standby?
- Hi sage, after detail inspects, I don't find any clue about async leak. And I don't get your point about async cause ...
- 05:05 PM Bug #12787: ceph-disk does not activate with systemd on some CentOS 7
- There is a race : udev add /dev/vdc1 runs ceph-disk trigger and if that happens bfore /dev/vdc1 is ready (i.e. before...
- 04:50 PM Revision bdb2fa24 (ceph): mds: Make sure wanted_state of first MDSBeacon is MDSMap::STATE_BOOT
- Fixes: #12506
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 04:32 PM Revision c6e681a9 (ceph): rgw: improve documentation for rgw_extended_http_attrs config opt.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 04:32 PM Revision eb7c21fd (ceph): rgw: add support for printing generic attrs on Swift container.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 04:32 PM Revision 8c2b8b7e (ceph): rgw: add support for printing generic attrs on Swift account.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 04:28 PM Revision 85bece77 (ceph): new release key
- The previous release key,
pub 4096R/460F3994 2015-09-15
uid Ceph.com (release key) <security@ceph... - 04:03 PM CephFS Bug #12506 (Fix Under Review): "Fuse mount failed to populate" error
- https://github.com/ceph/ceph/pull/5966
- 12:48 PM CephFS Bug #12506: "Fuse mount failed to populate" error
- this timeout only happens for jobs that contain clusters/standby-replay.yaml. I reproduce this issue locally by set "...
- 03:59 PM Revision 9d8fb1cb (ceph): rgw: camelcase also after dash in rgw_extended_http_attrs.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 03:56 PM Linux kernel client Bug #12695: rbd flatten makes clone's snap crash
- If it was that simple, it would have been backported :-)
At the very least you are going to need e8f59b595d05 ("rbd:... - 08:36 AM Linux kernel client Bug #12695: rbd flatten makes clone's snap crash
- Hi,thanks for your reply!
I have merge the code from 3.16 to 3.10.But it also have the same problem.
I have cha... - 03:44 PM Revision c029c434 (ceph): Merge pull request #5947 from weiqian/master
- doc: replaces 'osd host' with 'host' in ceph.conf docs.
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:52 PM CephFS Bug #13129 (Need More Info): qa: not starting ceph-mds daemons
- That commit is now about 16 hours old, and these jobs were started about 24 hours ago — although they didn't get mach...
- 07:52 AM CephFS Bug #13129: qa: not starting ceph-mds daemons
- the bug is introduced by commit 685d76a77ca16ca601a99148ef507cfde1fb3593 "ceph: wait for CephFS to be healthy before ...
- 02:47 PM Bug #12979: Ceph lost it's repair ability after repeatedly flapping
- It sounds like you need to adjust the mon_osd_min_down_reporters (default apparently 1) and mon_osd_min_down_reports ...
- 02:29 PM Revision 4cccde63 (ceph): Revert "Merge pull request #567 from ceph/ceph_fuse-timeout"
- This reverts commit ff1655cb57793f18698919f5284b1f207893ff8f, reversing
changes made to 2b25080d4faf0ae9ddb0000808830... - 02:05 PM Linux kernel client Bug #12763: rbd: unmap failed: (16) Device or resource busy
- i think the device may be being used by multipathd or something else....
- 08:45 AM Linux kernel client Bug #12763: rbd: unmap failed: (16) Device or resource busy
- The below is the operation in my vmware.The same operation is ok on the real machine.
[root@song ~]# rbd ls -p son... - 08:29 AM Linux kernel client Bug #12763: rbd: unmap failed: (16) Device or resource busy
- Well, that shouldn't be the case. What are the steps to reproduce on your vmware VM?
- 06:28 AM Linux kernel client Bug #12763: rbd: unmap failed: (16) Device or resource busy
- Thank you for your reploy!
I think this is relate to the vmvare.I install the same system and ceph in the real mac... - 12:56 PM CephFS Bug #13138: Segfault shutting down python-cephfs
- 12:48 PM CephFS Bug #13138 (Fix Under Review): Segfault shutting down python-cephfs
- https://github.com/ceph/ceph/pull/5964
- 10:36 AM CephFS Bug #13138: Segfault shutting down python-cephfs
- So perhaps we weren't seeing this in automated tests because you have to keep the process alive for a while after shu...
- 10:17 AM CephFS Bug #13138 (Resolved): Segfault shutting down python-cephfs
- ...
- 12:55 PM Revision 943558c9 (ceph): Merge pull request #5964 from jcsp/wip-13138
- libcephfs: fix calling init() then mount()
- 12:47 PM Revision 6a24d319 (ceph): libcephfs: fix calling init() then mount()
- Previously only ever called these separately, but
it should be allowed for callers to use one after
the other.
Fixes... - 12:31 PM rgw Bug #13140: rgw: swift API returns more than real object count and bytes used when retrieving acc...
- Related objects in the pool:
> sandy@ceph20:~$ rados -p .rgw.buckets ls
> default.64171.1__shadow_.... - 12:21 PM rgw Bug #13140 (Resolved): rgw: swift API returns more than real object count and bytes used when ret...
- For a subuser possessing one container and one object of 20M, its metadata may look like this:
sandy@ceph20:~$ curl ... - 11:32 AM rbd Feature #13139 (Duplicate): support output the supported configs which can be set via metadata
- it maybe just like:
$ rbd metadata config
Hmm, I'm not sure what's the suitable rbd command to do this thing. - 10:59 AM Revision 3b608565 (ceph): Merge pull request #5963 from jcsp/wip-cmake-cephfs
- CMake: fix libcephfs shared lib generation
- 10:54 AM Revision b8dc21e8 (ceph): Merge pull request #5857 from ceph/wip-da-SCA-20150812
- SCA and compiler warning fixes
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:52 AM Revision 6e8e0e7b (ceph): Merge pull request #5870 from s09816/master
- osd:the fuction osd::shutdown Lock failed.
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:51 AM Revision 47afe9ae (ceph): Merge pull request #5096 from tchaikov/wip-add-bl-const-iterator
- common/buffer: add bufferlist::const_iterator
Reviewed-by: Sage Weil <sage@redhat.com> - 10:27 AM Revision e017aab2 (ceph): CMake: fix libcephfs shared lib generation
- Previously weren't generating versioned symlinks
etc, so python bindings didn't find it.
Signed-off-by: John Spray <... - 09:47 AM Bug #13135: high mon memory usage after upgrade firefly -> hammer
- Here's another update. Now aleady over 610MB (started with 80MB)......
- 08:07 AM Bug #13135: high mon memory usage after upgrade firefly -> hammer
- Here's another update. Now aleady over 460MB (started with 80MB)......
- 07:20 AM Bug #13135: high mon memory usage after upgrade firefly -> hammer
- Update after about 1h since mon restart (cluster always healthy):...
- 07:08 AM Bug #13135 (Rejected): high mon memory usage after upgrade firefly -> hammer
- Yesterday I upgraded a firefly cluster to hammer 0.94.3. More info about my cluster and another issue can be found he...
- 09:09 AM Bug #13078 (Resolved): ceph-monstore-tool still create a local file when get map failed
- 09:09 AM Revision 3045168f (ceph): Merge pull request #5920 from caibo2014/fix-tool-bug
- tools: ceph_monstore_tool: remove the output file when get map fails
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:59 AM Revision 11e9c066 (ceph): Merge pull request #5960 from dachary/wip-13136-python3-coverage
- install-deps.sh: disable python3
Reviewed-by: Kefu Chai <kchai@redhat.com> - 07:35 AM Revision 7182499c (ceph): install-deps.sh: disable python3
- Disable python3 support until
https://bugs.launchpad.net/ubuntu/+source/python-coverage/+bug/1496715
is fixed.
Nothi... - 07:21 AM Bug #13130: qa:failed pool create in mkpool_layout_vxattrs.sh
- I reproduce this bug locally. the failure is because that monitors do not know correct path for crushtool
- 07:04 AM Revision b8c5d5b3 (ceph): rgw: clarify the error message when trying to create an existed user
- Modify the error message when trying to create an existed user to indicate which of uid, email or key actually causes...
- 03:14 AM Revision a825f686 (ceph): client/MetaRequest: optimize func can_forward/auth_is_best.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 03:07 AM Revision a1959284 (ceph): unify order limit
- Fixes: #13124
Signed-off-by: xinxin shu <xinxin.shu@intel.com> - 02:46 AM Bug #12983: handle_sub_read: Bad hash for 116/b1271c9d:test-rados-api-burnupi34-7183-66/foo/head
Compared to a simple run of just the single test case there is an extra _setattr_. In addition we can see the extr...- 02:35 AM rgw Bug #13133 (Resolved): rgw: empty s3 secret key should not be regarded as valid
- 02:05 AM Revision f51afa63 (ceph): client/MetaRequest: open w/ O_CREAT|O_TRUNC is write.
- From the function name is_write, it judge MetaRequest whether write.
For open, if it w/ O_CREAT|O_TRUNC, it's a write... - 01:57 AM Revision 8f46bd9c (ceph): clinet/MetaRequest: Remove the useless condition.
- "head.op & CEPH_MDS_OP_WRITE" include "head.op == CEPH_MDS_OP_CREATE".
So remove the conditon statement "head.op == C... - 12:45 AM devops Feature #13063: cobbler/ansible: put inktank-rescue image in cobbler-profiles role
- https://github.com/ceph/ceph-sepia-secrets/pull/39
- 12:42 AM devops Feature #13063 (Fix Under Review): cobbler/ansible: put inktank-rescue image in cobbler-profiles ...
- https://github.com/ceph/ceph-cm-ansible/pull/135
- 12:04 AM Bug #12936: shec fails i386 make check
- And just in case anybody else tries searching for it with the same string I did:, this is failing the qa/workunits/er...
- 12:03 AM Bug #12936: shec fails i386 make check
- If this is going to take some time can we back out the test (...or the plugin? :/) so that any new errors in i386 ar...
09/16/2015
- 10:49 PM Bug #13130 (Can't reproduce): qa:failed pool create in mkpool_layout_vxattrs.sh
- http://pulpito.ceph.com/teuthology-2015-09-12_23:04:01-fs-infernalis---basic-multi/1054419
This looks a lot like #... - 10:42 PM CephFS Bug #13129 (Rejected): qa: not starting ceph-mds daemons
- http://pulpito.ceph.com/teuthology-2015-09-14_23:10:02-knfs-master-testing-basic-multi/1057697
http://pulpito.ceph.c... - 10:23 PM CephFS Bug #12506: "Fuse mount failed to populate" error
- This is continuing to cause trouble in the nightlies. http://pulpito.ceph.com/teuthology-2015-09-14_23:04:02-fs-maste...
- 10:16 PM Bug #13128 (Won't Fix): mixed client firefly osd with hammer client - rados api test failure
- Config:
roles:
node1: mon.a osd.0 osd.1
node2: mon.b mon.c osd.2 osd.3
node3: client.0
node1 and node2 on 0.80... - 09:50 PM CephFS Fix #13126: qa: ceph-fuse flushes very slowly in some workunits
- This is blocked by/equivalent to #13127 in the Ceph project.
- 09:45 PM CephFS Fix #13126 (Resolved): qa: ceph-fuse flushes very slowly in some workunits
- Our ffsb and fsync workunits both generate lots of small IOs at random offsets, each of which becomes its own Op to t...
- 09:49 PM Bug #13127 (Resolved): ObjectCacher: coalesce multiple writes to a single object into one IO
- Right now, if the ObjectCacher has dirty data at multiple offsets of a single object, each contiguous region becomes ...
- 09:29 PM Revision 2f43e23f (ceph): Merge pull request #569 from dachary/wip-13031-packages
- buildpackages: fix flake / pep8
- 09:27 PM Revision f97fde6c (ceph): tasks/cephfs: switch unmount timeout to 15 minutes
- Our ffsb and fsync tests contain so many small writes at random offsets
that it can take >10 minutes to commit all of... - 09:21 PM Revision ff1655cb (ceph): Merge pull request #567 from ceph/ceph_fuse-timeout
- ceph: wait for CephFS to be healthy before proceeding
Reviewed-by: John Spray <john.spray@redhat.com> - 09:19 PM Revision e38a6d69 (ceph): buildpackages: build the repository and the packages
- http://tracker.ceph.com/issues/13031 Fixes: #13031
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:53 PM Revision 685d76a7 (ceph): ceph: wait for CephFS to be healthy before proceeding
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 08:28 PM Bug #12936: shec fails i386 make check
- 08:28 PM Bug #12748: bug with cache/tiering and snapshot reads [merged, needs a test in ceph-qa-suite]
- 08:28 PM RADOS Bug #11235: test_rados.py test_aio_read is racy
- 06:41 PM rbd Bug #13124 (Resolved): librbd order limits inconsistent with rbd cli
- ceph -v
ceph version 0.94.3 (95cefea9fd9ab740263bf8bb4796fd864d9afe2b)
Using librdb directly (for example by usin... - 06:33 PM rbd Documentation #13123 (Closed): document why striping should be useful
- Afaik rbd *always* splits the image into chunks of size 2^order (2^22 = 4MB by default).
What's the benefit of spe... - 06:27 PM rbd Bug #13122 (Resolved): rbd: stripingv2 feature bit not set when unnecessary for striping params
- ceph -v
ceph version 0.94.3 (95cefea9fd9ab740263bf8bb4796fd864d9afe2b)
rbd create --size 1024 --image-format 2 --... - 05:24 PM Feature #13121 (Resolved): osd: add pool level setting for recovery priority?
- Copy the email as below:...
- 05:22 PM Feature #13120 (New): osd: prioritize more degraded PGs for recovery by considering the missing_l...
- Copy the email as below:...
- 05:21 PM Revision 08bae3b9 (ceph): Use old branches as is without 'ceph-' for firefly, hammer etc
- Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
- 05:07 PM Bug #13119 (Can't reproduce): msg/async: does not wake up from standby?
- 04:50 PM Documentation #13118 (Closed): Are instructions available for building ceph on Debian Wheezy?
- I know there are existing packages for it, but hoping to build it myself. Are there instructions or build flags that...
- 03:31 PM Bug #13117 (Resolved): msgr creatse a zillion threads
- mark can reproduce this
- 02:51 PM devops Fix #12994 (Pending Backport): rbd-replay* should ship in ceph-common
- 01:12 PM devops Fix #12994 (Resolved): rbd-replay* should ship in ceph-common
- 02:04 PM Revision d0ac68bf (ceph): mon/PGMap: calc min_last_epoch_clean when decode
- Fixes: #13112
Signed-off-by: Kefu Chai <kchai@redhat.com> - 01:12 PM Revision 391cfb9f (ceph): Merge pull request #5841 from ceph/wip-12994-rbd-replay-packaging
- #12994: packaging: move rbd-replay* to ceph-common
Reviewed-by: James Page <jamespage@ubuntu.com>
Reviewed-by: Natha... - 01:11 PM Revision f389f6b8 (ceph): Merge pull request #5946 from liewegas/wip-rgw-logdir
- radosgw: log to /var/log/ceph instead of /var/log/radosgw
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 01:00 PM Bug #13116: osd: pg stuck in replay
- To get good coverage of this case we shoudl set replay interval for test pools to something short (5 or 10 seconds)
- 12:57 PM Bug #13116: osd: pg stuck in replay
- ...
- 12:51 PM Bug #13116 (Resolved): osd: pg stuck in replay
- "description": "osd_op(mds.0.172:22092466 1000fb5427c.00000000 [create 0~0,setxattr parent (347)] 0.e4638...
- 12:48 PM rbd Bug #13115 (Resolved): librbd python bindings eat exceptions in callbacks
- If an exception happens in a Python callback (e.g. the argument to rbd_image.diff_iterate), ctypes prints it out to s...
- 12:40 PM Bug #12100: OSD crash, uexpected aio error in FileJournal.cc
- Pontus Lindgren wrote:
> Happened again yesterday.
>
> We use two RAID mirrored SSD's as journals and have indivi... - 12:36 PM Bug #12983: handle_sub_read: Bad hash for 116/b1271c9d:test-rados-api-burnupi34-7183-66/foo/head
- /a/sage-2015-09-15_18:56:52-rados-wip-sage-testing---basic-multi/1058556
- 12:35 PM Bug #13114 (Resolved): LibRadosWatchNotify.WatchNotify2Timeout
- ...
- 11:36 AM Bug #13113 (Duplicate): common/Mutex.cc: 105: FAILED assert(r == 0)
- First seen at https://github.com/ceph/ceph/pull/5950#issuecomment-140698684...
- 07:27 AM Linux kernel client Bug #12691: ffsb osd thrash test - osd/ReplicatedPG.cc: 2348: FAILED assert(0 == "out of order op")
- That's a good point. Looking at the logs again, I mistook where the pg log trim happened - it was after the crash, so...
- 07:18 AM Bug #13112: should recalc the min_last_epoch_clean when decode PGMap
- https://github.com/ceph/ceph/pull/5950
- 07:11 AM Bug #13112 (Resolved): should recalc the min_last_epoch_clean when decode PGMap
- ...
- 06:05 AM Revision d1505b54 (ceph): doc: delete wrong description of installing RPMs
- In CentOS/RHEL 6/7, gitk and git-gui are available in default repository actually.
Signed-off-by: Li Peng <lip@dtdre... - 03:15 AM RADOS Bug #13111 (Fix Under Review): replicatedPG:the assert occurs in the fuction ReplicatedPG::on_loc...
- ...
- 03:09 AM Stable releases Tasks #13097: replicatedPG:the assert occurs in the fuction ReplicatedPG::on_local_recover.
- sorry?i submit the problem in the wrong project.please close this problem,i will submit this problem in the ceph proj...
- 03:04 AM Revision 1f7a2dc5 (ceph): doc:Replaces 'osd host' with 'host'
- Signed-off-by: weiqian <weiq@dtdream.com>
- 01:42 AM Bug #13110 (Resolved): osd: should accept delete op when full
- 12:52 AM Bug #13104: osd: slow requests stuck for a long time
- I don't have much debug information found from the cluster unless a perf dump:...
09/15/2015
- 11:56 PM Bug #12979: Ceph lost it's repair ability after repeatedly flapping
- In order to more clearly illustrate this problem , I 'll build a very simple cluster, only have one monitor and three...
- 11:56 PM Bug #12979: Ceph lost it's repair ability after repeatedly flapping
- Sage Weil wrote:
> from the logs this looks like a networking problem:
>
> [...]
> it can't talk to any other os... - 09:56 PM Bug #12979 (Closed): Ceph lost it's repair ability after repeatedly flapping
- from the logs this looks like a networking problem:...
- 10:16 PM Bug #12787: ceph-disk does not activate with systemd on some CentOS 7
- The problem can be reproduced reliably with http://cloud.centos.org/centos/7/images/CentOS-7-x86_64-GenericCloud-1508...
- 10:05 PM Revision c1b28591 (ceph): radosgw: log to /var/log/ceph instead of /var/log/radosgw
- This is simpler.
Signed-off-by: Sage Weil <sage@redhat.com> - 10:02 PM CephFS Bug #12895: Failure in TestClusterFull.test_barrier
- Hmm, this is a bit weird. I don't know why mount_a is sometimes holding on to caps that get revoked when mount_b cre...
- 09:42 PM Revision b615f35a (ceph): Merge remote-tracking branch 'gh/infernalis'
- 09:41 PM Bug #13109: msg/async leak, observed on mon
- hmm, mon uses loopback heavily and other stuff doesn't. maybe that's why this triggers there?
- 09:40 PM Bug #13109 (Resolved): msg/async leak, observed on mon
- /a/sage-2015-09-15_12:12:39-rados:verify-wip-sage-testing---basic-multi/1058089
all of the failures are processes ... - 09:40 PM Bug #13069 (Resolved): mon: many many leaks (MonSession?)
- 09:36 PM Revision 07893665 (ceph): Merge pull request #5725 from liewegas/wip-scrub-stats
- osd/ReplicatedPG: snaptimmer: adjust stats through ctx->delta_stats
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:35 PM Revision ba020808 (ceph): Merge pull request #5925 from liewegas/wip-mon-leaks
- fix various mon leaks
Reviewed-by: Joao Eduardo Luis <joao@suse.de> - 09:34 PM Bug #13068 (Resolved): osd: leaking transactions
- 09:34 PM Revision 3e42b4b5 (ceph): Merge pull request #5929 from liewegas/wip-osd-leaks
- misc osd leaks
Reviewed-by: David Zafman <dzafman@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com> - 09:18 PM Bug #12990: osd: we do not ignore notify from down osds
- 03:24 PM Bug #12990: osd: we do not ignore notify from down osds
- 09:18 PM Bug #13108: pg stat mismatch caused by double evict on same object
- 08:58 PM Bug #13108 (Resolved): pg stat mismatch caused by double evict on same object
- da68bb371f8b06b85a73077cd069a294193ac6c0 causes us to purge an obc from the cache when we proxy a write on it. This ...
- 09:14 PM CephFS Bug #12971 (Fix Under Review): TestQuotaFull fails
- 09:11 PM Revision 412e412a (ceph): osd: permit MDS to send writes on full pools
- Same behaviour as the global full flag, for the
per-pool full flag. The FS was broken by 67de12bf,
which added the p... - 09:04 PM Revision eab30086 (ceph): Revert "osd: purge the object from the cache when proxying and not prom...
- Fixes: #13108
This reverts commit da68bb371f8b06b85a73077cd069a294193ac6c0. - 08:35 PM Revision 494c2e44 (ceph): Merge pull request #5944 from tchaikov/wip-13090
- mds: cast numbers for mds health to string when print
Reviewed-by: John Spray <john.spray@redhat.com> - 08:30 PM Bug #13000: ceph-disk failure to activate with dmcrypt
- * ceph-disk prepare /dev/vdb
No activation
* partprobe /dev/vdb
Activates as expected
- 07:21 PM Bug #13000: ceph-disk failure to activate with dmcrypt
- > Also I notice that ceph-disk isn't logging to syslog properly? misc.log has some but not all output.. i'm guessing ...
- 03:48 PM Bug #13000 (In Progress): ceph-disk failure to activate with dmcrypt
- * https://github.com/ceph/ceph-qa-suite/tree/wip-13000-centos-activate
- 08:25 PM Revision 4d5d15c2 (ceph): osdc: fix honor_osdmap_full
- This was being ignored in new code that tested
the per-pool full flags. Refactor it so that
all the tests of full fl... - 08:25 PM Revision ca7861d2 (ceph): osdc/Objecter: make unlocked 'full' helpers private
- These never needed to be public, let's be safe.
Signed-off-by: John Spray <john.spray@redhat.com> - 08:12 PM CephFS Bug #13107: ceph-fuse: handle multiple mounts on the same host (don't set nonce with only PID)
- Yeah, Josh is working on a fix for this in all the clients. libcephfs apparently already solves this problem with 48 ...
- 08:09 PM CephFS Bug #13107: ceph-fuse: handle multiple mounts on the same host (don't set nonce with only PID)
- Hah, if I recall correctly I was a bit scandalised back in 2014 when I found out we treated a PID as a nonce :-) Set...
- 07:41 PM CephFS Bug #13107 (Resolved): ceph-fuse: handle multiple mounts on the same host (don't set nonce with o...
- See #13032. It's possible for multiple processes on the same host to have the same PID if they're in separate namespa...
- 08:01 PM Revision 96486fd6 (ceph): packaging: move rbd-replay* to ceph-common
- The rbd-replay* utilities are useful for Ceph users with RBD clients.
Currently the rbd-replay* utilities ship in the... - 07:39 PM Bug #13032: client nonce collision due to unshared pid namespaces
- I'd rather do incremental changes than muck around with the messenger interface internals to fix a bug we only see in...
- 07:28 AM Bug #13032: client nonce collision due to unshared pid namespaces
- Yeah, looks like we should just randomize it, as libcephfs does already: https://github.com/ceph/ceph/blob/f6bf6c2a96...
- 12:29 AM Bug #13032: client nonce collision due to unshared pid namespaces
- Sadly; adding a random number would probably be better than using /proc/self/ns/pid, it seems to increment when I mak...
- 12:02 AM Bug #13032: client nonce collision due to unshared pid namespaces
- It's hacky as hell (and quite linux specific); but I were about to readlink("/proc/self/ns/pid", .., ..) and extract ...
- 06:08 PM RADOS Bug #13106 (New): librados,objectstore: clarify behavior of 0 length write (does it extend the ob...
- 06:07 PM Revision f9d107a1 (ceph): osd_types.cc: add size to ObjectRecoveryInfo print
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 06:07 PM Revision f162e33f (ceph): src/test/osd/Object: allow a hole at the end of the object
- This way, we test the case with holes at the end of the file more
often.
Signed-off-by: Samuel Just <sjust@redhat.com> - 06:07 PM Revision 1d3e46be (ceph): ReplicatedBackend::prepare_pull: set recover_info.size for clones
- Fixes: #12828
Signed-off-by: Samuel Just <sjust@redhat.com> - 05:58 PM Revision 03b8ed3b (ceph): msg/simple: discard local queued messages on shutdown
- Otherwise these generate leak detection noise.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:58 PM Revision c842555c (ceph): mon: debug refs on output replies
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:56 PM rgw Bug #12920: HEAD requests on large MPU Swift objects consistently timeout
- Looks like this issue is related to the fact that Swift static large objects are not supported currently in Ceph (htt...
- 05:49 PM rgw Feature #5164 (Closed): rgw: multisite: metadata push notifications: design blueprint
- implemented as part of multisite v2.
- 05:48 PM rgw Feature #6999 (Resolved): Make RGW_MAX_PUT_SIZE configurable
- This was implemented a while back, using the rgw_max_put_size configurable.
- 05:47 PM rgw Feature #3366 (Resolved): rgw: dr: define management api
- Was done long long time ago
- 05:47 PM Bug #13104 (Need More Info): osd: slow requests stuck for a long time
- I'd missed that time jump. Still, I think we'd need something more to go on, especially since much of this has been c...
- 05:39 PM Bug #13104: osd: slow requests stuck for a long time
- So if the object is degraded and it is a recovery candidate, it would kick off the recovery for the object immediatel...
- 05:36 PM Bug #13104 (Won't Fix): osd: slow requests stuck for a long time
- The object is degraded and the OSD is waiting for it to get repaired.
Unless I'm missing some other aspect of the ... - 05:24 PM Bug #13104 (Rejected): osd: slow requests stuck for a long time
- # It is a bucket index object.
# There was continues writing to the buckets.
# The bucket index object is small (< ... - 05:36 PM rgw Feature #11138 (In Progress): rgw: export data via nfs
- 05:36 PM rgw Feature #12907 (In Progress): rgw: support object storage-class
- 05:36 PM rgw Feature #11412 (In Progress): rgw: tie ganesha fsal to librgw object interface
- 05:36 PM rgw Feature #11411 (In Progress): rgw: tie ganesha fsal to librgw bucket interface
- 05:33 PM rgw Feature #12905 (Fix Under Review): rgw: multisite: per-shard incremental sync stage
- 05:29 PM rgw Feature #4432: Develop plan for multi-user / multi-tenancy
- We have a plan
- 05:28 PM rgw Feature #7467 (Resolved): Make radosgw work with multiple hostnames
- 05:27 PM rgw Feature #10342 (Resolved): rgw: tool to clean up clutter
- This was implemented
- 05:25 PM rgw Feature #13105 (New): rgw::amazon id management::sts
- Prototype implementation of Amazon secure token service in support of idp integration.
- 05:22 PM rgw Feature #13103 (New): rgw: multisite: keep source zone property on objects
- 05:21 PM rgw Feature #13102 (Resolved): rgw: multisite: copy-if-newer option for data copy
- 05:20 PM rgw Feature #13099 (In Progress): rgw: multisite: data sync - init
- 05:18 PM rgw Feature #13099 (Resolved): rgw: multisite: data sync - init
- 05:19 PM rgw Feature #11410 (In Progress): rgw: implement object api to use with ganesha fsal (librgw)
- 05:19 PM rgw Feature #13101 (Resolved): rgw: multisite: data sync: incremental
- 05:18 PM rgw Feature #13100 (Resolved): rgw: multisite: data sync: full data sync
- 05:15 PM rgw Feature #11409 (In Progress): rgw: implement bucket api to use with ganesha fsal (librgw)
- 05:14 PM rgw Feature #11934 (Fix Under Review): rgw: metadata log sync work
- 05:12 PM rgw Feature #11944 (Fix Under Review): rgw: RESTful api for period operations
- 05:12 PM rgw Feature #11944: rgw: RESTful api for period operations
- 05:01 PM devops Bug #11798 (Pending Backport): upstart: configuration is too generous on restarts
- 05:01 PM devops Bug #11798: upstart: configuration is too generous on restarts
- We're planning to ship this fix downstream in the RHCS 1.2 series - we might as well get it upstream in Firefly too.
- 08:24 AM devops Bug #11798 (Resolved): upstart: configuration is too generous on restarts
- 04:53 PM Revision 137eb7e3 (ceph): mon/Monitor: fix MonSession Leak
- dispatch() does not need to keep a ref; we hold one indirectly
via the MonOpRequest.
Signed-off-by: Sage Weil <sage@... - 04:53 PM Revision 0b309e97 (ceph): mon: fix MonSession operator<<
- Print the object, not its pointer. Make output unambiguously
terminated.
Signed-off-by: Sage Weil <sage@redhat.com> - 04:53 PM Revision 89cc479e (ceph): mon: do not leak messages on shutdown
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:21 PM Revision 95462525 (ceph): mds: cast numbers for mds health to string when print
- MDSHealthMetric.metadata is a map<string,string>, so the num in
`m.metadata["foo"] = num` is casted to char when bein... - 04:08 PM Linux kernel client Bug #12691: ffsb osd thrash test - osd/ReplicatedPG.cc: 2348: FAILED assert(0 == "out of order op")
- Is the dup op log that small? That's <200 tids we are talking about.
Josh, can you attach those logs? It'd be inte... - 04:00 PM Linux kernel client Bug #12763: rbd: unmap failed: (16) Device or resource busy
- The location of osd dirs shouldn't matter here. Typically, you get -EBUSY on rbd unmap if your block device is still...
- 03:47 PM Linux kernel client Bug #12867 (Resolved): support CEPH_FEATURE_MSGR_KEEPALIVE2
- With "libceph: don't access invalid memory in keepalive2 path" and "libceph: advertise support for keepalive2" queued...
- 03:37 PM Revision 8c618e56 (ceph): buildpackages: re-use config from install task
- So that the packages built match what the install task expects.
http://tracker.ceph.com/issues/13031 Fixes: #13031
... - 02:55 PM Bug #13090 (Fix Under Review): ceph health detail format error in the mds0: line
- https://github.com/ceph/ceph/pull/5944
- 02:16 PM Bug #13090 (In Progress): ceph health detail format error in the mds0: line
- 02:44 PM Bug #12737 (Can't reproduce): pg stuck in WaitLocalBackfillReserved, asok unresponsive
- 02:43 PM Bug #12912 (Resolved): Messenger/MessengerTest.SyntheticInjectTest4/0 hang (asyncmsgr)
- 02:43 PM Bug #12967 (Duplicate): osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
- 02:16 PM Revision d40d8ff5 (ceph): buildpackages: pep8 compliance
- http://tracker.ceph.com/issues/13031 Fixes: #13031
Signed-off-by: Loic Dachary <loic@dachary.org> - 02:13 PM Revision 0eeb441b (ceph): buildpackages: build ceph packages and upload them
- Import install from task.
http://tracker.ceph.com/issues/13031 Fixes: #13031
Signed-off-by: Loic Dachary <loic@dach... - 01:53 PM Bug #12824 (Can't reproduce): osd/ReplicatedPG.cc: 10604: FAILED assert(obc) in hit_set_remove_all
- 01:53 PM Bug #13098 (Resolved): OSD crashed when reached pool's max_bytes quota
- [enviroment]
ceph version 0.94.3-196-g19ff928 (19ff92806fd1e0fb866737f58e379aa8078b8017)
[huangjun@code253 src]$ ... - 01:46 PM Bug #12974 (Can't reproduce): el7: /var/run/ceph mysteriously reverts to 770
- 01:45 PM Bug #13059: rpm upgrade does not fix /var/run/ceph ownership/permissions
- Boris Ranto wrote:
> RPM does fix the file/dir ownership on upgrade. What happens here is that these files are manag... - 01:44 PM Stable releases Tasks #13097 (Closed): replicatedPG:the assert occurs in the fuction ReplicatedPG::on_local_recover.
- -7> 2015-08-28 17:56:08.179961 7fa382c26700 5 -- op tracker -- seq: 387, time: 2015-08-28 17:56:08.179961, event: ...
- 01:40 PM Revision 97ea80ca (ceph): Merge remote-tracking branch 'gh/infernalis'
- 01:38 PM Feature #11443: Elector: throttle election attempts from DoSing peers
- Sage,
backporting the respawn thresholds for upstart helps with some cases, but not the case where we originally s... - 01:25 PM Revision 5dfcd3ff (ceph): Merge pull request #5916 from xiaoxichen/fix1
- os/OSD.cc cast osd_max_write_size to int64_t
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:22 PM Revision a59cd6f9 (ceph): Merge pull request #5940 from flyd1005/master
- doc: Fixes a wrong directory name and a broken hyperlink
Reviewed-by: Abhishek Lekshmanan <abhishek.lekshmanan@ril.com> - 01:18 PM Revision 422d290c (ceph): Merge pull request #5912 from badone/bug_7822
- examples: hello_world.cc: fix the displayed content
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: Kefu ... - 01:14 PM Revision 646e53c1 (ceph): Merge pull request #5933 from dachary/wip-max-stale
- common: osd_pg_epoch_persisted_max_stale < map_cache_size
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:13 PM rgw Bug #13096 (Resolved): rgw: The type of caps can be any value.
- When executing the command of [radosgw-admin caps add --uid=wkm --caps="122=write"], the results show we add caps suc...
- 12:55 PM Revision 71f65295 (ceph): doc: fix a broken hyperlink
- Signed-off-by: Li Peng <lip@dtdream.com>
- 12:37 PM CephFS Feature #12137: cephfs-data-scan: backward scan of dirfrag objects, inject orphans
non-fragmented-dir case: https://github.com/ceph/ceph/pull/5941- 12:21 PM Revision 4b3ccc69 (ceph): Merge pull request #5934 from cernceph/wip-logrotate
- logrotate: logs are now owned by ceph:ceph
Reviewed-by: Sage Weil <sage@redhat.com> - 12:06 PM Revision bbe27dc6 (ceph): doc: Fixes a wrong directory name.
- Signed-off-by: Li Peng <lip@dtdream.com>
- 11:24 AM CephFS Bug #13067: MDSRank unhealthy on hammer -> infernalis upgrade
- 08:36 AM CephFS Bug #13067 (Fix Under Review): MDSRank unhealthy on hammer -> infernalis upgrade
- https://github.com/ceph/ceph/pull/5937/files
- 10:36 AM Revision 98ded95a (ceph): Merge pull request #5937 from ukernel/wip-13067
- Wip 13067
Reviewed-by: John Spray <john.spray@redhat.com> - 10:01 AM Revision 2b25080d (ceph): buildpackages: build ceph packages and upload them
- Build Ceph packages from source for the required revision, os_type,
os_version and architecture and upload them to th... - 09:47 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- The issue in this ticket was a problem triggered by a change to the core kernel and is fixed. The follow up comments...
- 09:25 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- Hi!
Are there any news here?
We are still having exactly the same issues with our cluster. And our *ONLY* usecase... - 09:45 AM Revision 8499d380 (ceph): Merge pull request #560 from dachary/wip-13026-hammer-stop
- hammer-x: test CEPH_FEATURE_HAMMER_0_94_4
- 08:58 AM Revision 26bcb362 (ceph): Examples: hello_world.cc, content displayed after read is not null term...
- Copy contents of bufferlist to a string before sending to stdout since a
bufferlist is not null terminated.
Fixes: #... - 08:41 AM Bug #12936 (In Progress): shec fails i386 make check
- 08:34 AM Revision 4e8242a0 (ceph): mds: reset MDSRank heartbeat timeout even when MDS is laggy
- Fixes: #13067
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 08:24 AM devops Backport #13091 (Resolved): upstart: configuration is too generous on restarts
- this backport has not been tested
- 08:23 AM Revision 2b11a4c0 (ceph): Merge pull request #5930 from liewegas/wip-11798-hammer
- upstart: limit respawn to 3 in 30 mins (instead of 5 in 30s)
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:15 AM Revision 807a34cc (ceph): common: osd_pg_epoch_persisted_max_stale < map_cache_size
- 1ff51a299d20dd73a95ba55fdec57498b8c71c13 reduced map_cache_size to 200,
osd_pg_epoch_persisted_max_stale must be lowe... - 07:57 AM rgw Bug #13095 (In Progress): rgw: MDlog will not output correctly
- By executing the command of "radosgw-admin mdlog list", if we only specify the option of "--end-date", eg."radosgw-ad...
- 07:53 AM Feature #12740: ceph-objetstore-tool: add operations to remove clone ids from a head or snapdir
- Hi @David, any progress on this?
do you need any help? - 07:15 AM CephFS Support #13055 (Closed): Problem with disconnect fuse by mds
- 06:50 AM CephFS Support #13055: Problem with disconnect fuse by mds
- thx. topic can be closed
- 06:46 AM CephFS Support #13055: Problem with disconnect fuse by mds
- Yes, we have fixed it. But the fix was not included in any release (We fix it after releasing v0.94.3), You need to ...
- 06:21 AM CephFS Support #13055: Problem with disconnect fuse by mds
- i have found the SAME problem at ceph tracker: http://tracker.ceph.com/issues/12297
logs are the same as into the 12... - 07:10 AM Revision 73d7bed9 (ceph): logrotate: logs are now owned by ceph:ceph
- Add the su directive to avoid this error during logrotate:
error: skipping "/var/log/ceph/ceph-osd.0.log" because pa... - 07:10 AM Linux kernel client Bug #13081: data on rbd image get corrupted when pool quota is smaller than the size of the rbd i...
- This is due to http://tracker.ceph.com/issues/12018 - fixed on the osd and userspace client. Moving this to the kerne...
- 07:08 AM rbd Bug #12018 (Resolved): rbd and pool quota do not go well together
- osd: commit:67de12bf9b67c29bf613e831f4146ff9809e42f7 client: commit:dbcf2e40d3e8a92f280879c74b7ca954a902b2d1 test: co...
- 06:31 AM rbd Backport #13045 (New): rbd export-diff crashes in librbd::simple_diff_cb
- Thanks Jason! This backport is yours now.
- 06:24 AM Backport #13094: Pipe: Drop connect_seq increase line
- this backport was not tested prior to merge
- 06:23 AM Backport #13094 (Resolved): Pipe: Drop connect_seq increase line
- https://github.com/ceph/ceph/pull/5908
- 06:23 AM Bug #13093 (Resolved): Pipe: Drop connect_seq increase line
- https://github.com/ceph/ceph/commit/67225cb3ee1f6d274a02293724942bdb25cec8ca
- 06:15 AM Bug #12647: Ceph log rotation backup strategy leads to log stop recording
- Sage Weil wrote:
> The logrotate script shoudl be rotating by doing a reload already.. can you attach your logrotate... - 05:36 AM Bug #13074: tcmalloc segfaults in Pipe::writer() when bufferlist goes out of scope
- Sorry this isn't clearer Greg. Unfortunately the failed formatting isn't helping and I can't find a way to edit my or...
- 01:33 AM Revision 7250fb18 (ceph): os/OSD.cc cast osd_max_write_size to int64_t
- Otherwise overflow may occur and negative values generated.
Signed-off-by: Xiaoxi Chen <xiaoxi.chen@intel.com> - 01:20 AM Documentation #13092 (Closed): Cache tiering, clarification on cache miss behaviour
- I'm opening this bug on the request of gregsfortytwo, who was very helpful in a brief discussion on IRC (#ceph-devel)...
- 12:16 AM Revision 95d5e38e (ceph): Merge pull request #564 from ceph/wip-hammer-x
- fixes for hammer-x
- 12:14 AM Revision 2460ce3b (ceph): upgrade/hammer-x: hammer test.sh before and during upgrade
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:14 AM Revision 39f9ce60 (ceph): upgrade/hammer-x/split-*: ignore osdmap encode errors
- This is normal during upgrade.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:09 AM Revision 139b5d62 (ceph): os: require Sequencer arg for apply_transaction()
- Signed-off-by: Sage Weil <sage@redhat.com>
09/14/2015
- 10:34 PM Bug #13032: client nonce collision due to unshared pid namespaces
- Yes, that would do it: https://github.com/ceph/ceph/blob/da96a89033590277460aef1c80f385bd93d625e1/src/librados/RadosC...
- 10:27 PM Feature #11443: Elector: throttle election attempts from DoSing peers
- Yes, getting the good and bad behaviors right is hard. Remember this needs to be something that each monitor can trac...
- 08:47 PM Feature #11443: Elector: throttle election attempts from DoSing peers
- https://github.com/ceph/ceph/pull/5930
- 08:43 PM Feature #11443: Elector: throttle election attempts from DoSing peers
- Trivial workaround here is backporting the respawn thresholds for upstart?
- 10:13 PM Bug #13090: ceph health detail format error in the mds0: line
- Kefu, can you check if this is just an output error, and if not pass it on the FS project?
- 09:04 PM Bug #13090 (Resolved): ceph health detail format error in the mds0: line
- While testing the Ceph File System, I noticed the mds0: line shows num_segments as "T" when I ran *ceph health detail...
- 10:00 PM devops Backport #13091 (In Progress): upstart: configuration is too generous on restarts
- 10:00 PM devops Backport #13091 (Resolved): upstart: configuration is too generous on restarts
- https://github.com/ceph/ceph/pull/5930
- 10:00 PM devops Bug #11798 (Pending Backport): upstart: configuration is too generous on restarts
- 08:47 PM devops Bug #11798: upstart: configuration is too generous on restarts
- https://github.com/ceph/ceph/pull/5930 (hammer backport)
- 09:57 PM Revision 0022c035 (ceph): Merge pull request #5908 from liewegas/wip-simple-connect-hammer
- Pipe: Drop connect_seq increase line
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 09:53 PM Bug #13089: mon: check for store writeablility before participating in election
- Mmm, I'm not sure we want to do the naive thing (write a file and fsync) on every election as that will slow them dow...
- 07:36 PM Bug #13089 (Resolved): mon: check for store writeablility before participating in election
- 09:35 PM Bug #13074: tcmalloc segfaults in Pipe::writer() when bufferlist goes out of scope
- I'm not quite following all the jumps between different code blocks here. What scenario is this crash appearing in? D...
- 12:00 AM Bug #13074 (Can't reproduce): tcmalloc segfaults in Pipe::writer() when bufferlist goes out of scope
- @
ceph version 0.94.2 (5fb85614ca8f354284c713a2f9c610860720bbf3)
1: /usr/bin/ceph-osd() [0xacb3ba]
2: (()+0x1034... - 09:31 PM Bug #12903 (Resolved): No longer able to host rbd images on cache-tier backed by EC pool
- 08:44 PM Revision b3822f11 (ceph): upstart: limit respawn to 3 in 30 mins (instead of 5 in 30s)
- It may take tens of seconds to restart each time, so 5 in 30s does not stop
the crash on startup respawn loop in many... - 08:40 PM Bug #13083 (Resolved): centos7: systemd unit specifies 2^32, process as 2^16 nofile ulimit
- https://github.com/ceph/ceph/pull/5923
- 06:22 PM Bug #13083: centos7: systemd unit specifies 2^32, process as 2^16 nofile ulimit
- max is 1048576 apparently
- 04:22 PM Bug #13083 (Resolved): centos7: systemd unit specifies 2^32, process as 2^16 nofile ulimit
- observed on bigbang
- 08:40 PM Revision 7d89225a (ceph): Merge pull request #5923 from ceph/wip-limits
- set limits in systemd unit files
- 08:36 PM Bug #13068 (Fix Under Review): osd: leaking transactions
- https://github.com/ceph/ceph/pull/5929
- 06:26 PM Bug #13068 (In Progress): osd: leaking transactions
- 01:50 PM Bug #13068: osd: leaking transactions
- i am looking at this, no progress so far.
- 08:33 PM Revision 16c672c7 (ceph): os/newstore: kill default_osr
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:33 PM Revision e7b57cd0 (ceph): os/newstore: better sequencer debug
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:33 PM Revision 83c83e44 (ceph): os/KeyValueStore: kill default_osr
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:33 PM Revision 1002201a (ceph): os/KeyValueStore: better osr debug
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:33 PM Revision df921125 (ceph): ceph_objectstore_test: fix warnings
- In file included from test/objectstore/store_test.cc:34:0:
../src/gmock/gtest/include/gtest/gtest.h: In instantiation... - 08:33 PM Revision 10b00f09 (ceph): os/FileStore: assert Sequencer is passed in; kill default_osr
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:33 PM Revision b46cdc02 (ceph): os/ObjectStore: fix leak ref on Sequencer_impl
- This should start at 0 refs, not 1.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:33 PM Revision 47e7953c (ceph): os/FileStore: improve debug output for sequencers
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:33 PM Revision fedf360a (ceph): osd: queue all transactions under an osr
- This was missed in e7bbafa3bfbd5e936a8be026a30b83a89f6121c3.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:19 PM Revision 583a2959 (ceph): rgw: json dump rgw_obj::orig_obj
- useful for debugging
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:19 PM Revision d5f8c8e4 (ceph): rgw: unit test for testing rgw_obj encoding correctness
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:19 PM Revision 470afb9c (ceph): rgw: rgw_obj encoding fixes
- Fix a few issues:
- conversion to and from rgw_obj_key
- strip_namespace_from_object() in the case where object sta... - 08:19 PM Revision 988979c3 (ceph): rgw: transform from cls_rgw_obj_key to rgw_obj correctly
- Fixes: #12819
cls_rgw_obj_key keeps object names encoded, so need to transform from
it to rgw_obj correctly.
Signed-... - 08:17 PM devops Feature #13063 (In Progress): cobbler/ansible: put inktank-rescue image in cobbler-profiles role
- The files are here: http://apt-mirror.front.sepia.ceph.com/inktank-rescue/
- 08:05 PM CephFS Fix #11187 (Resolved): ceph-qa-suite: reduce required machine numbers
- This is done for the regular suite, at least, and has not been provoking new problems that I can tell.
- 07:59 PM rgw Bug #13015 (Pending Backport): rgw: intra region copy does not preserve acl
- 07:54 PM Bug #12936: shec fails i386 make check
- This still happens:...
- 06:42 PM Bug #13088: a73a4cb breaks "--without-libatomic-ops" (firefly)
- That's odd:...
- 06:33 PM Bug #13088 (Resolved): a73a4cb breaks "--without-libatomic-ops" (firefly)
- The following commit causes a build-failure when built "@--without-libatomic-ops@": https://github.com/ceph/ceph/comm...
- 06:00 PM Revision 8453a89c (ceph): systemd: set nofile limit in unit files
- Make it big so hopefully nobody has to change it.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:00 PM Revision 367c794c (ceph): systemd: no need to preprocess ceph-osd@service
- This used to be necessary but now is not.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:00 PM Revision 8e13d89f (ceph): systemd: eliminate ceph-rgw tmpfiles.d file
- This is for storing the rgw socket files for fastcgi, which we do not
want to enable by default.
Signed-off-by: Sage... - 04:34 PM Feature #13079 (Fix Under Review): ceph-monstore-tool can get map info in human-readable
- https://github.com/ceph/ceph/pull/5921
- 08:20 AM Feature #13079 (Resolved): ceph-monstore-tool can get map info in human-readable
- if we want to see a map in human readable format.
we should:
(1) ceph-monstore-tool mon-store-path get monmap -- ... - 04:31 PM Revision 1ff51a29 (ceph): osd: drop default map cache size from 500 -> 200
- OSDs don't need this from each other anymore since they send
a pg_interval_map_t with pg notify. This cache is only ... - 04:24 PM Feature #13084 (New): ceph-disk: will not work with an software array (md) as journal destination
- [root@ceph001 ~]# ceph-disk -v prepare --fs-type xfs --cluster ceph -- /var/lib/ceph/osd/sdi0sdj /dev/md/sdi0sdj1
DE... - 04:04 PM Revision 8678a8ac (ceph): kill /etc/security/limits.d/ceph
- This only affects login shells; not useful.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:43 PM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Is the data that you see new, or is it the same old data that leaked before running 0.94.3? What do you see when you ...
- 03:43 PM rbd Backport #13045: rbd export-diff crashes in librbd::simple_diff_cb
- I don't think this issue will cleanly backport -- let me know if you want me to backport it.
- 03:30 PM rbd Bug #13082 (Fix Under Review): Valgrind memcheck detects out-of-bounds memory read
- *master PR*: https://github.com/ceph/ceph/pull/5926
- 03:23 PM rbd Bug #13082 (Resolved): Valgrind memcheck detects out-of-bounds memory read
- http://qa-proxy.ceph.com/teuthology/teuthology-2015-09-11_23:00:07-rbd-master---basic-multi/1051993/teuthology.log
- 03:27 PM Revision adb8478b (ceph): include/inline_memory: out-of-bounds read on unaligned memory
- When checking if a >=16 byte unaligned buffer is zeroed, the 32bit
check will read outside the buffer memory range.
... - 03:15 PM Revision 0b03b32d (ceph): tools:remove the local file when get map failed.
- Signed-off-by: Bo Cai <cai.bo@h3c.com>
- 02:37 PM Bug #12421 (Won't Fix): "failed to encode map <nap> with expected crc" when mon on hammer and OSD...
- This is normal and expected.
- 02:24 PM Revision c2a9764f (ceph): mon: do not return ref to MonOpRequest::get_session() caller
- Most callers don't put the ref, and since we hold the op ref it's
not necessary. This will also make a somewhat cle... - 02:19 PM Linux kernel client Bug #13081 (Resolved): data on rbd image get corrupted when pool quota is smaller than the size o...
- 1. linux kernel is 4.1.1...
- 02:12 PM Bug #11680 (Can't reproduce): mon crashes when "ceph osd tree 85 --format json"
- 02:12 PM Bug #11680: mon crashes when "ceph osd tree 85 --format json"
- quote of Kefu's inquiry
> Eino, i was looking at your issue at http://tracker.ceph.com/issues/12876.
> seems it i... - 09:14 AM Bug #11680: mon crashes when "ceph osd tree 85 --format json"
- sent mail to Eino for more information.
- 09:13 AM Bug #11680 (Need More Info): mon crashes when "ceph osd tree 85 --format json"
- quote Eino's report:
> >
> > I'm getting a segmentation fault error from the monitor of our test
> > cluster. Th... - 01:56 PM Revision d99e6899 (ceph): mon: fix MonSession leak when waitlisting op
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:43 PM Bug #13080 (Rejected): python-rados in PyPI / with python3 ?
- Hello,
I am currently testing ceph, and would be very happy if python-rados was available in python3.
One of the ... - 01:33 PM Bug #13078 (Fix Under Review): ceph-monstore-tool still create a local file when get map failed
- https://github.com/ceph/ceph/pull/5920
- 08:09 AM Bug #13078 (Resolved): ceph-monstore-tool still create a local file when get map failed
- when i try to get a map that dose not exist, it print an error, but still create a local file.
*here is the comman... - 01:22 PM Revision 6ca59302 (ceph): osd: should use ec_pool() when checking for an ecpool
- we were using pool.info.require_rollback() in do_osd_ops() when
handling OP_SPARSE_READ to tell if a pool is an ecpoo... - 01:22 PM Revision 64b22dcb (ceph): ceph_test_rados: also send sparse_read in ReadOp
- Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 5ae2e7a185b5f95753a09a89d7110fc38848a083)
Con... - 01:22 PM Revision 8849f993 (ceph): ceph_test_rados_api_io: add tests for sparse_read
- Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 4d4920610ebfcb516630ed15678979c9e9292f5a)
Co... - 01:22 PM Revision cecd68d0 (ceph): ceph_test_rados_api_aio: add a test for aio_sparse_read
- Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 076bad955d374cbb37b77e2b0429f3c85f32abc0) - 01:22 PM Revision 31804991 (ceph): osd: translate sparse_read to read for ecpool
- Fixes: #12012
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 700d42ef1c82f5602249b96690ae881c... - 01:02 PM CephFS Support #13055: Problem with disconnect fuse by mds
- Sergey Mir wrote:
> Thx,for now i need to wait next disconnect of fuse to look the message log...
> Besides,i have ... - 11:17 AM CephFS Support #13055: Problem with disconnect fuse by mds
- Thx,for now i need to wait next disconnect of fuse to look the message log...
Besides,i have changed filestore queue... - 08:02 AM CephFS Support #13055: Problem with disconnect fuse by mds
- make sure /var/log/ceph directory exist and have proper permission. add "debug client = 20" to client section of ceph...
- 07:28 AM CephFS Support #13055: Problem with disconnect fuse by mds
- there is no such log files on the client side where ceph-fuse is using...
as i understand logging is turned off, so ... - 06:34 AM CephFS Support #13055: Problem with disconnect fuse by mds
- Sergey Mir wrote:
> Zheng Yan wrote:
> Can you find any clue in ceph-fuse.log?
>
> there is no ceph-fuse.log on... - 06:21 AM CephFS Support #13055: Problem with disconnect fuse by mds
- Sergey Mir wrote:
> ceph-fuse process still works after "disconnect" so i should make umount and only then mount to ... - 06:19 AM CephFS Support #13055: Problem with disconnect fuse by mds
- Sergey Mir wrote:
> hello, is there any way to fix the problem?
try "ceph daemon client.xxx kick_stale_sessions" - 05:18 AM CephFS Support #13055: Problem with disconnect fuse by mds
- hello, is there any way to fix the problem?
- 12:33 PM Feature #13077: osd: new pool settings: scrub_interval, deep_scrub_interval
- https://github.com/ceph/ceph/pull/5922
- 07:40 AM Feature #13077 (Resolved): osd: new pool settings: scrub_interval, deep_scrub_interval
- Right now it is possible to control frequency of scrub runs via config using these parameters:
osd_deep_scrub_int... - 12:33 PM Feature #13076: osd: new pool flags: noscrub, nodeep-scrub
- https://github.com/ceph/ceph/pull/5922
- 07:26 AM Feature #13076 (Resolved): osd: new pool flags: noscrub, nodeep-scrub
- Right now it is possible to disable scrub and deep-scrub for the whole cluster:
ceph osd set noscrub
ceph osd... - 12:29 PM Bug #12755: selinux: ceph-mon denial on wip-user
- Lowering the priority as this does not seem to happen after the patch, the underlying issue is likely still there, th...
- 09:32 AM rgw Bug #13020 (Fix Under Review): rgw: include RequestId as part of the Error response
- 09:29 AM Revision d903df51 (ceph): tools:Removing duplicate references
- Signed-off-by: Bo Cai <cai.bo@h3c.com>
- 09:19 AM Bug #13059: rpm upgrade does not fix /var/run/ceph ownership/permissions
- RPM does fix the file/dir ownership on upgrade. What happens here is that these files are managed by systemd and syst...
- 08:52 AM rgw Bug #12761 (Pending Backport): Keystone Fernet tokens break auth
- Since affected version is hammer, I'm marking this for hammer backport. It is upto the leads to decide if the backpor...
- 08:50 AM Revision 2f663d90 (ceph): rgw: make radosgw-admin user rm idempotent
- Fixes: #5378
Signed-off-by: Orit Wasserman <owasserm@redhat.com> - 08:18 AM Backport #12835 (Fix Under Review): mon: map_cache can become inaccurate if osd does not receive ...
- 07:03 AM Revision fef7142c (ceph): ceph: fix rename into sub-directory check
- the check is important for FreeBSD because there is such check
in its kernel.
Signed-off-by: Yan, Zheng <zyan@redhat... - 06:34 AM rgw Backport #13047: Content-Type header should have correct initial capitals
- Assigning to me until kmroz gets tracker privileges.
- 04:13 AM Bug #13069: mon: many many leaks (MonSession?)
- sage, could you cherry-pick mine? https://github.com/tchaikov/ceph/tree/wip-monsession-leak
- 02:08 AM Bug #13069 (In Progress): mon: many many leaks (MonSession?)
- 02:08 AM Bug #13069: mon: many many leaks (MonSession?)
- 02:07 AM Bug #13069: mon: many many leaks (MonSession?)
- I got as far as github.com:liewegas/ceph wip-mon-leaks. We are still leaking MonSession (4 refs worth!).
- 02:04 AM Revision 40c3c85a (ceph): mon: debug MonSession refs
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:04 AM Bug #13075: ms async: msg throttle busy loops?
- Why I don't find "remote" dir at /a/sage-2015-09-12_17:44:29-rados-wip-sage-testing---basic-multi/1052889 ?
Is mes... - 01:17 AM Bug #13075 (Can't reproduce): ms async: msg throttle busy loops?
- ...
- 01:48 AM Revision 640ebbfa (ceph): mon/PGMonitor: fix use-after-free in stats ack
- The MonOpRequestRef owns one ref; we need to get() another so we
can pass it to send_reply.
Signed-off-by: Sage Weil... - 01:44 AM Revision 68ecc55d (ceph): mon: do not leak ref creating MonOpRequest
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:42 AM Revision 3a7d91d2 (ceph): msg/simple: debug refs on sent messages
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:36 AM Revision 7d112c64 (ceph): mon/MDSMonitor: drop incorrect m->put()
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:13 AM Bug #12990: osd: we do not ignore notify from down osds
- /a/sage-2015-09-12_17:44:29-rados-wip-sage-testing---basic-multi/1052905
09/13/2015
- 08:00 PM rgw Backport #13047 (In Progress): Content-Type header should have correct initial capitals
- someone is working on this - more info soon
- 02:16 PM Feature #13073 (New): automatically set journal file name as osd.{osd-num} with ceph-deploy.
- I ran this as a test:
??ceph-deploy osd prepare ceph01-osd02:sdb:/mnt/??
And output is:... - 01:45 PM Messengers Bug #13072 (Can't reproduce): osd_ping messages not getting through
- /a/sage-2015-09-12_17:44:29-rados-wip-sage-testing---basic-multi/1052646
a reset happens on one of the two hb conn... - 01:28 PM Revision 0d6a8c63 (ceph): Pipe: Drop connect_seq increase line
- Revert commit 0fc47e267b6f8dcd4511d887d5ad37d460374c25.
When accepting and "connect.connect_seq == existing->connect... - 01:12 PM Messengers Bug #13001 (Resolved): segfault in EventCenter::process_events(int)
- 01:12 PM Revision 27d1e4d4 (ceph): Merge pull request #5901 from yuyuyu101/wip-13001
- AsyncMessenger: Kepp file_lock hold when accessing its event field
- 01:12 PM Revision 786f23c5 (ceph): Merge pull request #5626 from majianpeng/objecter
- Objecter: fix bus about objecter.
Reviewed-by: Sage Weil <sage@redhat.com> - 01:12 PM Bug #13071 (Resolved): objecter: cancellation bugs
- https://github.com/ceph/ceph/pull/5626
- 01:09 PM Bug #12991 (Resolved): Error EINVAL: next mdsmap epoch 15 != 14
- 01:08 PM Revision c625671c (ceph): Merge pull request #5840 from liewegas/wip-12991
- qa/workunits/cephtool/test.sh: make mds epoch check more tolerant
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:31 PM Backport #13070 (Resolved): ceph-object-corpus: add 0.94.2-207-g88e7ee7 hammer objects
- https://github.com/ceph/ceph/pull/5551
- 12:13 PM rbd Backport #12597 (Resolved): Crash during shutdown after writeback blocked by IO errors
- 12:10 PM Revision 23fb8113 (ceph): Merge pull request #5767 from dachary/wip-12597-hammer
- Crash during shutdown after writeback blocked by IO errors
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 11:53 AM Bug #13026 (Resolved): require osds are hammer v0.94.4 or later before upgrading past hammer
- 09:49 AM Bug #13026 (Fix Under Review): require osds are hammer v0.94.4 or later before upgrading past hammer
- 11:45 AM Revision 770a573b (ceph): Merge remote-tracking branch 'gh/infernalis'
- 11:42 AM Revision c1849ecf (ceph): Merge pull request #5687 from liewegas/wip-hammer-feature-hammer
- include/ceph_features: define HAMMER_0_94_4 feature
- 11:41 AM Revision e73ac661 (ceph): Merge pull request #5686 from liewegas/wip-hammer-feature
- require osds are hammer v0.94.4 or later before upgrading past hammer
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 02:11 AM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Hi Yehuda,
Do you have an update on this bug?
I'm running Ceph 0.94.3 with civetweb and I've run some tests wit... - 12:44 AM Revision cac601d6 (ceph): Merge pull request #5905 from ceph/wip-rpm-notcmalloc
- ceph.spec: respect CEPH_EXTRA_CONFIGURE_ARGS
- 12:43 AM Revision f8c66b41 (ceph): Merge pull request #5904 from ceph/wip-submodules
- fix a few submodule issues
Reviewed-by: Loic Dachary <ldachary@redhat.com>
09/12/2015
- 10:46 PM Revision 5befd50e (ceph): hammer-x: test CEPH_FEATURE_HAMMER_0_94_4
- http://tracker.ceph.com/issues/13026 Refs: #13026
Signed-off-by: Loic Dachary <loic@dachary.org> - 09:43 PM Revision af39f98b (ceph): .gitignore: ignore src/ceph.tmpe
- It makes the gitbuilders unhappy. Not sure where it comes from...
Signed-off-by: Sage Weil <sage@redhat.com> - 06:21 PM Revision 98302adf (ceph): gmock: ignore *.pyc
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:17 PM Revision c57e8688 (ceph): rocksdb: ignore m4
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:12 PM Revision 51abff11 (ceph): ceph.spec: respect CEPH_EXTRA_CONFIGURE_ARGS
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:51 PM Revision 4a5a5b37 (ceph): qa/workunits/cephtool/test.sh: make mds epoch check more tolerant
- This can race with an actual mdsmap epoch update for some other
reason. We just need to make sure the epoch *increas... - 05:45 PM Revision a511c245 (ceph): Merge remote-tracking branch 'gh/wip-10617-again'
- 04:54 PM CephFS Support #13055: Problem with disconnect fuse by mds
- ceph-fuse process still works after "disconnect" so i should make umount and only then mount to back to work...
- 04:05 PM Revision 9429b773 (ceph): Merge pull request #5334 from majianpeng/read-len-zero-for-ec
- make read ec-object(offset=0, len=0) can work like read no-ec object.
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:14 PM CephFS Bug #13067: MDSRank unhealthy on hammer -> infernalis upgrade
- Hmm, kinda interesting that it's happening at the point in the log where the mons are restarted. Something in monc b...
- 12:38 PM CephFS Bug #13067 (Resolved): MDSRank unhealthy on hammer -> infernalis upgrade
- ...
- 01:24 PM Revision 4977d394 (ceph): Merge pull request #563 from ceph/wip-13060
- fix test for 11429 (and now 13060)
- 01:23 PM Backport #13060 (Resolved): osd: hammer: fail to start due to stray pgs after firefly->hammer upg...
- 01:23 PM Revision f35c53df (ceph): Merge pull request #5892 from ceph/wip-13060-hammer
- osd: allow peek_map_epoch to return an error
Reviewed-by: David Zafman <dzafman@redhat.com> - 01:22 PM Revision f0c925e3 (ceph): suites/rados/singleton-nomsgr/all/11429.yaml: double-hop and fix
- - simplify this.. lots of extra cruft we don't need
- restart twice at hammer to ensure that we can still load pgs
... - 01:21 PM Revision 4be8a28d (ceph): osd/PG: peek_map_epoch: skip legacy PGs if infos object is missing
- - pg is removed
- osd is stopped before pg is fully removed
- on restart, we ignore/skip the pg because its epoch is ... - 01:20 PM Revision f237ed97 (ceph): osd: allow peek_map_epoch to return an error
- Allow PG::peek_map_epoch to return an error indicating the PG
should be skipped.
Signed-off-by: Sage Weil <sage@redh... - 01:20 PM Revision f15d9585 (ceph): osd: allow peek_map_epoch to return an error
- Allow PG::peek_map_epoch to return an error indicating the PG
should be skipped.
Signed-off-by: Sage Weil <sage@redh... - 01:20 PM Revision d33fea5d (ceph): sd/PG: tolerate missing pgmeta object
- Bug 10617 left stray PG dirs around in firefly. Hammer correctly
ignores these, assuming they are leftover cruft. W... - 01:19 PM Revision 2e44373e (ceph): Merge pull request #5776 from wonzhq/tmap-update
- osd: force promote for ops which ec base pool can't handle
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by... - 01:17 PM Bug #13069 (Resolved): mon: many many leaks (MonSession?)
- /var/lib/teuthworker/archive/sage-2015-09-11_13:17:43-rados-wip-sage-testing---basic-multi/1050645
my guess is Mon... - 01:15 PM Bug #13068 (Resolved): osd: leaking transactions
- ...
- 12:33 PM Revision ff9600a6 (ceph): osd/ReplicatedPG: remove stray debug line
- This snuck in
Signed-off-by: Sage Weil <sage@redhat.com> - 09:36 AM Messengers Bug #13001 (Fix Under Review): segfault in EventCenter::process_events(int)
- 09:34 AM Revision 6e854338 (ceph): AsyncMessenger: Kepp file_lock hold when accessing its event field
- When process_event get a file event, other thread may delete this event later
but before we do event
Fix #13001
Sign... - 07:37 AM rgw Documentation #13066 (Resolved): Document radosgw keystone admin user & tenant options
- Similar to other openstack service configurations, rgw seems to support the option of a service tenant and user being...
09/11/2015
- 10:36 PM devops Feature #13063 (Resolved): cobbler/ansible: put inktank-rescue image in cobbler-profiles role
- also, find a place to store the relevant files, even if just temporarily. apt-mirror.front?
- 10:01 PM Documentation #12899 (In Progress): Update the 'rados' command "man" page
- Updated the 'rados' command "man" pages to include the '--run-name' option under the 'bench' sub-command.
-https:/... - 09:12 PM Bug #13032: client nonce collision due to unshared pid namespaces
- You can strike "--ipc" as well, concurrent invocations on the same machine of "unshare --pid --fork -- rbd list" trig...
- 08:38 PM Bug #13032: client nonce collision due to unshared pid namespaces
- I'm guessing namespaces aren't entirely supported yet.
Essentially; my reduced breaking testcase.
Makefile wi... - 06:55 PM Bug #13032: client nonce collision due to unshared pid namespaces
- One other potential contributing factor, multiple invocations of rbd list on the same host running within different m...
- 05:58 PM Bug #13032: client nonce collision due to unshared pid namespaces
- I don't think this is regarding fd's, while I didn't run it under RLIMIT_NOFILE/RLIM_INFINITY, judging by attaching s...
- 04:58 PM Bug #13032: client nonce collision due to unshared pid namespaces
- Josh Durgin wrote:
> This looks like the client is running into the fd limit, preventing it from opening a socket to... - 02:45 AM Bug #13032: client nonce collision due to unshared pid namespaces
- This looks like the client is running into the fd limit, preventing it from opening a socket to receive a reply, and ...
- 02:03 AM Bug #13032 (Resolved): client nonce collision due to unshared pid namespaces
- We have a process which concurrently ends up starting 3 jobs concurrently which among other things do a mix of rbd li...
- 08:55 PM Revision 37559f50 (ceph): Merge pull request #562 from ceph/wip-radosbench-cleanup
- tasks/radosbench: allow cleanup: false
- 08:52 PM Revision 5af28cf7 (ceph): tasks/radosbench: allow cleanup: false
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:44 PM Backport #13060: osd: hammer: fail to start due to stray pgs after firefly->hammer upgrade
- https://github.com/ceph/ceph-qa-suite/pull/563
- 08:04 PM Backport #13060: osd: hammer: fail to start due to stray pgs after firefly->hammer upgrade
- reproduced the failure with a modified 11429.yaml... now verifying the fix.
- 03:02 PM Backport #13060 (Fix Under Review): osd: hammer: fail to start due to stray pgs after firefly->ha...
- https://github.com/ceph/ceph/pull/5892
- 02:09 PM Backport #13060 (Resolved): osd: hammer: fail to start due to stray pgs after firefly->hammer upg...
- https://github.com/ceph/ceph/pull/5892
On Fri, 11 Sep 2015, Haomai Wang wrote:
> On Fri, Sep 11, 2015 at 8:56 PM,... - 08:40 PM Revision f3f41417 (ceph): doc: Updated the rados command man page to include the --run-name optio...
- Fixes: #12899
Signed-off-by: ritz303 <ritz_303@yahoo.com> - 05:59 PM rbd Feature #13025 (Fix Under Review): Add scatter/gather support to librbd C/C++ APIs
- 01:11 AM rbd Feature #13025: Add scatter/gather support to librbd C/C++ APIs
- Adding new methods to the C API:...
- 05:43 PM rgw Bug #12537: [CVE-2015-5245] RGW returns requested bucket name raw in "Bucket" response header
- Please see https://www.owasp.org/index.php/HTTP_Response_Splitting for an explanation about HTTP header manipulation ...
- 05:30 PM Feature #11443: Elector: throttle election attempts from DoSing peers
- What about a model like
void behaved()
void disappointed()
bool should_ignore()
with a couple exponential... - 05:19 PM Bug #13059: rpm upgrade does not fix /var/run/ceph ownership/permissions
- I think we need the equivalent of
https://github.com/ceph/ceph/blob/master/debian/ceph-common.postinst#L67-L86 - 01:50 PM Bug #13059 (Resolved): rpm upgrade does not fix /var/run/ceph ownership/permissions
- /a/sage-2015-09-10_16:14:42-rados-wip-sage-testing---basic-multi/1049102
- 05:13 PM Backport #12940 (Fix Under Review): IO error on kvm/rbd with an erasure coded pool tier (after an...
- https://github.com/ceph/ceph/pull/5897
- 04:08 PM Backport #12940 (In Progress): IO error on kvm/rbd with an erasure coded pool tier (after an upgr...
- 09:27 AM Backport #12940 (New): IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from...
- 05:02 PM Revision 78de6fd6 (ceph): Merge pull request #5896 from liewegas/wip-fix-spec
- ceph.spec: include /etc/sysconfig/ceph
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 04:21 PM Bug #12722: osd: OSD::do_mon_report stuck at acquiring osd_lock (more than 10mins) and cause OSD ...
- Sorry for the delayed work on this one, I will make a PR next week.
- 04:20 PM Revision e9847570 (ceph): Merge pull request #561 from ceph/wip-sudo
- sudo ceph
- 04:19 PM Revision 4dea76e0 (ceph): ceph.spec: include /etc/sysconfig/ceph
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:19 PM Revision 22dc3df4 (ceph): Merge pull request #559 from ceph/wip-10328
- leaks
- 04:15 PM Revision dad981d3 (ceph): tasks: sudo ceph for cli
- /var/run/ceph is 770. This is mainly necessary for any
interaction with the daemon sockets, but it is what users do
... - 04:15 PM Revision 5eb0e4dd (ceph): suites: sudo ceph
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:01 PM CephFS Support #13055: Problem with disconnect fuse by mds
- when "transported point is not connected" happen, could you check if the ceph-fuse process still exists. If not, run ...
- 02:35 PM CephFS Support #13055: Problem with disconnect fuse by mds
- and about high load... i've checked mds nodes for memory overload or some other physical overload - didnt find anythi...
- 02:31 PM CephFS Support #13055: Problem with disconnect fuse by mds
- Zheng Yan wrote:
Can you find any clue in ceph-fuse.log?
there is no ceph-fuse.log on clients...
fuse have same... - 02:26 PM CephFS Support #13055: Problem with disconnect fuse by mds
- dmesg and other clients logs are empty...
i have 5 clients with mounted to ceph.
3 of them are using more often(ma... - 02:20 PM CephFS Support #13055: Problem with disconnect fuse by mds
- "Transport endpoint is not connected" almost always means that the ceph-fuse client process has gone away. Check dmes...
- 02:20 PM CephFS Support #13055: Problem with disconnect fuse by mds
- Zheng Yan,
yes,as i pasted earlier in my config, i have changed it to mds_session_autoclose = 60 - 02:19 PM CephFS Support #13055: Problem with disconnect fuse by mds
- Sergey Mir wrote:
> fuse is just disconnecting from ceph and says "transported point is not connected" and thats all... - 02:14 PM CephFS Support #13055: Problem with disconnect fuse by mds
- >> 2015-09-10 13:11:17.068839 mds.0 [INF] closing stale session client.343916 (client_ip):0/8623 after 64.626196
MDS... - 01:59 PM CephFS Support #13055: Problem with disconnect fuse by mds
- fuse is just disconnecting from ceph and says "transported point is not connected" and thats all, no logs or some oth...
- 01:41 PM CephFS Support #13055: Problem with disconnect fuse by mds
- We need to know how the system is misbehaving -- not just to see log snippets.
What is the symptom of the problem ... - 12:59 PM CephFS Support #13055: Problem with disconnect fuse by mds
- Need some solution to solve that problem. it drops again...
2015-09-11 15:42:57.450895 7fb118d06700 0 -- (mds00/m... - 11:09 AM CephFS Support #13055: Problem with disconnect fuse by mds
- fuse loose connections few times a day with output in logs as i pasted at my previous message from few different log ...
- 10:43 AM CephFS Support #13055: Problem with disconnect fuse by mds
- The log snippets you've pasted don't make much sense — you have some entries going back in time, and it looks like th...
- 10:25 AM CephFS Support #13055 (Closed): Problem with disconnect fuse by mds
- Hello. Nobody knows answer in hex chat(ceph) about, so im asking advice here.
i have ceph version 0.94.3 (95cefea9fd... - 03:56 PM Revision f5c8735d (ceph): Merge pull request #5895 from jcsp/wip-doc-default-pools
- doc: remove references to default data/metadata pools
- 03:53 PM Revision 9b3f36f9 (ceph): ceph: add option to expect valgind errors and fail if there are none
- See #10328
Signed-off-by: Sage Weil <sage@redhat.com> - 03:53 PM Revision 822fa666 (ceph): rados/singleton-nomsgr/all/valgrind-leaks: verify leak checking works
- Fixes: #10328
Signed-off-by: Sage Weil <sage@redhat.com> - 03:46 PM Revision 86570812 (ceph): doc: remove references to default data/metadata pools
- These haven't existed since 0.84 -- the cephfs documentation
was updated at the time, but there were also references ... - 03:44 PM Bug #12976 (Resolved): debian jessie: /var/run/ceph not created
- 03:42 PM Revision 89e2c28c (ceph): Merge pull request #5803 from ceph/wip-debian-systemd
- debian systemd support; /etc/{sysconfig,default}/ceph; easy jemalloc enablement
Reviewed-by: Ken Dreyer <kdreyer@red... - 03:38 PM Revision ea91c4ef (ceph): systemd: tmpfiles.d in /run, not /var/run
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:38 PM Revision c3d23cad (ceph): ceph-common: explicitly trigger /run/ceph creation
- This doesn't happen magically on debian.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:38 PM Revision c8bfc354 (ceph): ceph.spec: install /etc/sysconfig/ceph
- Make it easy to enable jemalloc, too.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:38 PM Revision cd4bd80a (ceph): Makefile.am: include etc in tarball
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:38 PM Revision 7384a14f (ceph): debian/rules: install systemd files and /etc/default/ceph
- Fix the systemd units to use /etc/default instead of /etc/sysconfig. There
is probably a better way...
Signed-off-b... - 03:38 PM Revision c92d13b0 (ceph): debian: fix location of tmpfiles.d
- /usr/lib/tmpfiles.d, not /lib/tmpfiles.d
Signed-off-by: Sage Weil <sage@redhat.com> - 03:36 PM Revision 6779bc2d (ceph): Merge pull request #5869 from ceph/wip-rpm-dirs
- ceph.spec: make /var/{lib,log,run} owned by ceph
Reviewed-by: Boris Ranto <branto@redhat.com> - 03:31 PM Revision cbb8cf83 (ceph): Merge pull request #5540 from ceph/wip-selinux-radosgw
- selinux: Update policy for radosgw
Reviewed-by: Milan Broz <mbroz@redhat.com> - 03:26 PM Revision 3aa38bc0 (ceph): make /var/run/ceph 770 ceph:ceph
- This allows members of the ceph group to make librados clients (like the
ceph cli and qemu) create sockets in the def... - 03:24 PM Revision e7837d1d (ceph): ceph.spec: make /var/{lib,log,run} owned by ceph
- Move creation of /var/lib/ceph and /var/run/ceph to ceph-common, too.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:23 PM Bug #12387: osd/PG.cc: 6879: FAILED assert(pg->peer_info.count(so))
- https://github.com/ceph/ceph/pull/5780
- 03:22 PM Bug #12387: osd/PG.cc: 6879: FAILED assert(pg->peer_info.count(so))
- 65dcc2da76750d0b6dd2cf0031c44f32749f33e5
- 03:04 PM Bug #13026: require osds are hammer v0.94.4 or later before upgrading past hammer
- https://github.com/ceph/ceph/pull/5686...
- 02:48 PM Bug #13061 (Resolved): systemd: daemons restart when package is upgraded
- I just updated some ceph-mon and ceph-osd hosts from ceph-9.0.3-1460.g4290d68.el7.x86_64 to ceph-9.0.3-1572.g90cce11....
- 02:44 PM Backport #13035 (In Progress): requeue_scrub when kick_object_context_blocked
- 08:57 AM Backport #13035 (Resolved): requeue_scrub when kick_object_context_blocked
- https://github.com/ceph/ceph/pull/5891
- 02:40 PM Backport #13037 (In Progress): hit set clear repops fired in same epoch as map change -- segfault...
- 08:59 AM Backport #13037 (Resolved): hit set clear repops fired in same epoch as map change -- segfault si...
- https://github.com/ceph/ceph/pull/5890
- 02:27 PM Backport #13042 (In Progress): ThreadPool add/remove work queue methods not thread safe
- 09:04 AM Backport #13042 (Resolved): ThreadPool add/remove work queue methods not thread safe
- https://github.com/ceph/ceph/pull/5889
- 01:47 PM Backport #13036 (In Progress): osd: avoid multi set osd_op.outdata in tier pool
- 08:58 AM Backport #13036 (Resolved): osd: avoid multi set osd_op.outdata in tier pool
- https://github.com/ceph/ceph/pull/6060
- 01:37 PM CephFS Backport #13044 (In Progress): LibCephFS.GetPoolId failure
- 09:06 AM CephFS Backport #13044 (Resolved): LibCephFS.GetPoolId failure
- https://github.com/ceph/ceph/pull/5887
- 01:35 PM Revision 7e7179b4 (ceph): Merge pull request #5871 from liewegas/wip-10328
- common: add debug option to deliberately leak some memory
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:33 PM rbd Backport #13045 (In Progress): rbd export-diff crashes in librbd::simple_diff_cb
- 09:07 AM rbd Backport #13045 (Resolved): rbd export-diff crashes in librbd::simple_diff_cb
- https://github.com/ceph/ceph/pull/6097
- 01:30 PM Revision 08781399 (ceph): Merge remote-tracking branch 'gh/wip-tcmalloc'
- 01:30 PM Revision f167e8d3 (ceph): .gitignore: radosgw-object-expirer
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:29 PM Bug #13058: Ceph destroyed my MBR record when trying to convert it to GPT after initiating a new ...
- The whole output is:...
- 01:05 PM Bug #13058 (Can't reproduce): Ceph destroyed my MBR record when trying to convert it to GPT after...
- Hi
I have my OS on sda and the OS use sda1-3 now I wanted to initiate a new OSD and ran with this command:
And I... - 01:24 PM Fix #13033 (Resolved): logrotate: error in postrotate script
- 08:27 AM Fix #13033 (In Progress): logrotate: error in postrotate script
- 07:35 AM Fix #13033: logrotate: error in postrotate script
- https://github.com/ceph/ceph/pull/5881
- 07:28 AM Fix #13033 (Resolved): logrotate: error in postrotate script
- The simplified logrotate scripts give this error:...
- 01:24 PM Revision 90cce118 (ceph): Merge pull request #5881 from cernceph/wip-logrotate
- logrotate: ignore exit status 1 from killall
Reviewed-by: Sage Weil <sage@redhat.com> - 01:19 PM CephFS Bug #12971 (In Progress): TestQuotaFull fails
- Looks like this commit might have broken it:...
- 01:01 PM Bug #13057 (Resolved): python-setuptools is missing from debian/control
- If I run a package build from the current git master, I get this error after about 90 minutes of compilation:
<pre... - 12:49 PM Backport #13034 (In Progress): osd: copy-from doesn't preserve truncate_{seq,size}
- 08:52 AM Backport #13034 (Resolved): osd: copy-from doesn't preserve truncate_{seq,size}
- https://github.com/ceph/ceph/pull/5885
- 11:51 AM Revision d8ac5103 (ceph): WorkQueue: add/remove_work_queue methods now thread safe
- These methods were not acquiring the ThreadPool lock when
manipulating the work_queue collection. This was causing
o... - 11:45 AM Documentation #13056 (Closed): Stale link for jerasure
- http://ceph.com/docs/master/rados/operations/erasure-code-jerasure/ links to https://bitbucket.org/jimplank/jerasure/...
- 11:01 AM Revision 3a50b904 (ceph): crypto: fix unbalanced ceph::crypto::init/ceph::crypto:shutdown
- we may create a CephContext without calling common_init_finish(), then
delete the CephContext. In this case, ceph::cr... - 10:35 AM Revision 0a5b8569 (ceph): ReplicatedPG,Objecter: copy_get should include truncate_seq and size
- Otherwise, we break CephFS over cache tiers.
Fixes: #12551
Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry pic... - 10:20 AM rados-java Bug #7488 (Rejected): "Error EAGAIN: osd.0 is not up" in rados-master-testing-basic-plana
- 10:20 AM rados-java Bug #7425 (Rejected): Error in run_seed_to_range.sh for rados-dumpling-master-basic-plana
- 10:19 AM rados-java Bug #7413 (Rejected): LibRadosTier.FlushTryFlushRaces failed on rados:basic-wip-agent-testing-bas...
- 10:19 AM rados-java Bug #10023 (Resolved): method Rados.shutdown() is missing for closing the connection to the clust...
- The shutdown has been implemented. This should be fixed now.
- 10:19 AM Stable releases Tasks #11644: firefly v0.80.11
- ...
- 10:18 AM rados-java Bug #7479 (Won't Fix): Test failed in rados-dumpling-testing-basic-plana
- Does not seem to be a RADOS Java bug. Closing this one.
- 10:17 AM rados-java Bug #9988 (Resolved): Rbd.list() / list contains one element, if pool is empty
- This has been fixed in the latest release of RADOS Java.
- 10:17 AM rados-java Bug #9989 (Resolved): Rbd.list() / more than 1024 images in pool?
- This is also fixed in the latest release of RADOS Java.
- 10:16 AM rados-java Bug #9990 (Resolved): Rbd.list() / JVM crashes
- The RADOS Java bindings have been improved and they should not crash on this.
Resolving this as fixed. - 10:12 AM Revision 45c9c0ae (ceph): distros: alias a-supported-distro.yaml to CentOS 7
- Some jobs are distribution agnostic and it is meaningless to run them on
all supported distributions. For such jobs i... - 09:41 AM rgw Fix #12939: Content-Type header should have correct initial capitals
- removing infernalis from the Backport field: before infernalis is released, scheduling something to be in infernalis ...
- 09:16 AM rgw Backport #13054 (Resolved): rgw: region data still exist in region-map after region-map update
- https://github.com/ceph/ceph/pull/6163
- 09:15 AM rgw Backport #13053 (Resolved): GWWatcher::handle_error -> common/Mutex.cc: 95: FAILED assert(r == 0)
- https://github.com/ceph/ceph/pull/6164
- 09:13 AM rgw Backport #13052 (Resolved): rgw: init_rados failed leads to repeated delete
- https://github.com/ceph/ceph/pull/6165
- 09:12 AM rgw Backport #13051 (Rejected): rgw: init_rados failed leads to repeated delete
- 09:10 AM rgw Backport #13048 (Resolved): Content-Type header should have correct initial capitals
- https://github.com/ceph/ceph/pull/5532
- 09:09 AM rgw Backport #13047 (Resolved): Content-Type header should have correct initial capitals
- https://github.com/ceph/ceph/pull/5910
- 09:09 AM Revision 2dbf2018 (ceph): compat: define XATTR_CREATE/XATTR_REPLACE for FreeBSD
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 09:09 AM Revision 38262031 (ceph): compat: define O_DSYNC for FreeBSD
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 09:09 AM Revision be595df5 (ceph): compat: include compat.h for definition of ENODATA
- ENODATA is not defined on FreeBSD. Include compat.h for all places
that use ENODATA
Signed-off-by: Yan, Zheng <zyan@... - 09:09 AM Revision b4330832 (ceph): compat: include proper headers for FreeBSD
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 09:09 AM Revision c4fe2661 (ceph): compat: don't reinterpret_cast NULL
- On FreeBSD, NULL is defined as nullptr_t. We get following error
error: reinterpret_cast from 'nullptr_t' to 'foo *'... - 09:09 AM Revision 80655e15 (ceph): memstore: don't use thread_local on non-linux OS
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 09:08 AM rgw Backport #13046 (Resolved): RGW : setting max number of buckets for user via ceph.conf option
- https://github.com/ceph/ceph/pull/6166
- 09:08 AM Revision e5a8022d (ceph): ceph.spec.in: ceph-radosgw should require ceph-selinux
- Signed-off-by: Boris Ranto <branto@redhat.com>
- 09:08 AM Revision 338bd3d1 (ceph): selinux: Update policy for radosgw
- The current SELinux policy does not cover radosgw daemon. This patch
introduces the SELinux support for radosgw daemo... - 09:05 AM Backport #13043 (Resolved): ThreadPool add/remove work queue methods not thread safe
- https://github.com/ceph/ceph/pull/5991
- 09:03 AM Backport #13041 (Resolved): common/Thread:pthread_attr_destroy(thread_attr) when done with it
- https://github.com/ceph/ceph/pull/6325
- 09:03 AM Backport #13040 (Resolved): common/Thread:pthread_attr_destroy(thread_attr) when done with it
- https://github.com/ceph/ceph/pull/6157
- 09:01 AM Backport #13039 (Resolved): hammer: osd/PG.cc: 6879: FAILED assert(pg->peer_info.count(so))
- https://github.com/ceph/ceph/pull/8464
- 09:00 AM Backport #13038 (Resolved): hit set clear repops fired in same epoch as map change -- segfault si...
- https://github.com/ceph/ceph/pull/5988
- 08:27 AM rados-java Support #12474 (Rejected): rados.dll not found in resource path
- The bindings are currently Linux only and there is no Windows support for them currently.
- 08:26 AM rados-java Bug #12937 (Won't Fix): WriteFull Hangs when the Server is down
- That is how RADOS works. You can set a osd_op_timeout as a setting and it will. But by default it will never return i...
- 08:03 AM Bug #12100: OSD crash, uexpected aio error in FileJournal.cc
- Happened again yesterday.
We use two RAID mirrored SSD's as journals and have individual HDDs as OSD data disks. W... - 08:02 AM Revision 645f3e90 (ceph): mds: For journal, set write iohint flags.
- For rank, if there is a standby replay rank, we don't use
fadvise_dontneed for write ops. Except this case, we use
fa... - 07:42 AM Revision 217e4248 (ceph): logrotate: ignore postrotate error for radosgw
- Fix the annoying logrotate error for radosgw.
Fixes: #13033
Signed-off-by: Dan van der Ster <daniel.vanderster@cern.ch> - 07:30 AM Revision aa4a5b0d (ceph): logrotate: ignore exit status 1 from killall
- If any of ceph-osd, ceph-mon, ceph-mds were not running then
killall -q will exit status 1, leading to anacron sendin... - 05:31 AM Bug #12681: tcmalloc doesn't release memory back to system
- https://github.com/kuszmaul/SuperMalloc seem precent well performance.
- 05:07 AM Revision fa6e4fff (ceph): osdc/Journaler: add write_ihont filed which record the write fadvise fl...
- This filed will send to osd for write ops which make osd can better
handle.
Signed-off-by: Jianpeng Ma <jianpeng.ma@... - 05:07 AM Revision 7c09e508 (ceph): osdc/Objecter: make sg_read/write support iohint_flags.
- 05:07 AM Revision 9b44fab0 (ceph): osdc/Filer: make read/write support iohint flags.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 05:07 AM Revision 4b45e6d1 (ceph): osdc/Objecter: pass extra_ops of read_full into read func.
- We don't know extra_ops whether null, so pass it to read func is good
method.
Signed-off-by: Jianpeng Ma <jianpeng.m... - 05:07 AM Revision 7e3c7a45 (ceph): osdc/Journaler:: For read operation add fadvise-dontneed flag.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 04:33 AM rgw Bug #13018: rgw/rgw_admin: Checking the legality of the parameters
- https://github.com/ceph/ceph/pull/5879
- 02:38 AM Revision ffad2828 (ceph): rgw:modify the conditional statement in parse_metadata_key method.
- Signed-off-by: Zengran Zhang <zhangzengran@h3c.com>
- 02:35 AM Revision f4498f52 (ceph): osd:the fuction osd::shutdown Lock failed.
- Fixed:#13004
Signed-off-by: Lu Shi <shi.lu@h3c.com> - 02:11 AM Revision 648c7041 (ceph): os: disable newstore when configure --without-libaio
- newstore makes extensive use of aio. So disable it when configure
--without-libaio
Signed-off-by: Yan, Zheng <zyan@r... - 02:11 AM Revision 6359f3ae (ceph): cls_numops: don't include asm-generic/errno.h directly
- It's not portable
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 02:11 AM Revision d7f1d709 (ceph): memstore: don't encode/decode 'size_t'
- there is no encode/decode funtions for type 'size_t'. We get following
error on OSX:
os/PageSet.h:207:5: error: call... - 02:03 AM CephFS Bug #12806: nfs restart failures
- 01:13 AM rbd Feature #12698 (Fix Under Review): librbd: write maintenance operations to journal
- *master PR*: https://github.com/ceph/ceph/pull/5735
09/10/2015
- 11:08 PM devops Bug #12227 (Resolved): mira030 has bad disk
- Drive 7 replaced, testnodes role run, system nuked, and returned to service.
- 10:50 PM Bug #12966: ceph-post-file key should only be readable by root
- I think the problem is that debian enforces everything in /usr/share/foo is 644.. my attempts to chmod otherwise aren...
- 10:48 PM Revision 48c42286 (ceph): Merge pull request #5800 from ceph/wip-user
- ceph-disk: do async startup on upstart; fix dmcrypt create/activate bug
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:03 PM Revision d4eeb9be (ceph): rocksdb: recognized --without-tcmalloc
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:42 PM Revision 86dbfc88 (ceph): Merge pull request #5031 from trociny/wip-10098
- ceph-objectstore-tool: add mark-complete operation
Reviewed-by: David Zafman <dzafman@redhat.com> - 08:14 PM Revision fa94ca4e (ceph): Merge pull request #5866 from jmunhoz/wip-requestid-on-error
- rgw: include RequestId as part of the Error response
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 08:13 PM Revision a795c885 (ceph): common/buffer: add the move constructor for bufferlist
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 08:07 PM Bug #12100: OSD crash, uexpected aio error in FileJournal.cc
- Sage Weil wrote:
> It's interesting that the EIO is always preceeded by slow requests... about 30-35 seconds old. W... - 08:04 PM Bug #12100: OSD crash, uexpected aio error in FileJournal.cc
- Sage Weil wrote:
> It's interesting that the EIO is always preceeded by slow requests... about 30-35 seconds old. W... - 07:44 PM Bug #12100: OSD crash, uexpected aio error in FileJournal.cc
- Lukas Pustina wrote:
> Sage Weil wrote:
> > 18446744073709551611 == 0xfffffffffffffffb -> -5 (EIO). check kern.log... - 07:17 PM Bug #12100: OSD crash, uexpected aio error in FileJournal.cc
- Sage Weil wrote:
> 18446744073709551611 == 0xfffffffffffffffb -> -5 (EIO). check kern.log for errors on your disk?
... - 07:25 PM rgw Bug #12537: [CVE-2015-5245] RGW returns requested bucket name raw in "Bucket" response header
- This is now being tracked as CVE-2015-5245.
- 07:16 PM Revision 1b43d811 (ceph): common/buffer: fix the const-ness of bufferlist::contents_equal()
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 07:09 PM Revision 6504e373 (ceph): common/buffer: add bufferlist::const_iterator
- * implement bufferlist::iterator using bufferlist::iterator_impl
* unlike its cousin, `bufferlist::const_iterator` is... - 07:09 PM Revision 8ed72422 (ceph): test/bufferlist: do not expect !is_page_aligned() after unaligned rebuild
- if the size of a bufferlist is page aligned we allocate page aligned
memory chunk for it when rebuild() is called. ot... - 07:04 PM Revision 046bdf8e (ceph): Merge pull request #5859 from jecluis/wip-test-mon-ping
- test: mon/mon-ping.sh: make sure 'ceph mon ping' works as expected
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:45 PM Revision 50c9beeb (ceph): Merge pull request #5873 from dillaman/wip-rbd-missing-return
- rbd: missing return statement within do_metadata_remove
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 05:32 PM Linux kernel client Bug #12691: ffsb osd thrash test - osd/ReplicatedPG.cc: 2348: FAILED assert(0 == "out of order op")
- Josh,
can you let me know what values I can try for osd_min_pg_log_entries and osd_max_pg_log_entries. - 02:10 AM Linux kernel client Bug #12691: ffsb osd thrash test - osd/ReplicatedPG.cc: 2348: FAILED assert(0 == "out of order op")
- Increasing osd_min_pg_log_entries and osd_max_pg_log_entries should avoid the problem. We should probably add that to...
- 02:04 AM Linux kernel client Bug #12691: ffsb osd thrash test - osd/ReplicatedPG.cc: 2348: FAILED assert(0 == "out of order op")
- Looking at the osd logs, it seems like in one case at least this happened due to dup op detection having limited hist...
- 01:50 AM Linux kernel client Bug #12691: ffsb osd thrash test - osd/ReplicatedPG.cc: 2348: FAILED assert(0 == "out of order op")
- Does this problem make sense http://tracker.ceph.com/issues/12691
- 05:29 PM Revision 5a2b688c (ceph): src/.gitignore: add some more files to be ignored
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:29 PM Revision b229162e (ceph): client/Client.cc: fix memory leak, free sgids in error case
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:29 PM Revision 4a2377c4 (ceph): rgw_object_expirer_core.cc: remove left over unused variable
- Remove unused variable is_next_available and while loop. These
are leftovers from commit #a69a989f.
Signed-off-by: D... - 05:29 PM Revision 534fdd5c (ceph): ErasureCodeShecTableCache.cc: prefer --operator for non-primitive itera...
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:29 PM Revision a1be9ef4 (ceph): NewStore.cc: prefer --/++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:29 PM Revision 120071bc (ceph): osd/OSD.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:29 PM Revision 0297ce19 (ceph): osd/ReplicatedPG.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:29 PM Revision 2767736a (ceph): osdc/Objecter.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:29 PM Revision 6e97b0fa (ceph): rbd.cc: fix -Wreturn-type, return result from do_metadata_remove()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:29 PM Revision d9d49890 (ceph): Transaction.c: replace deprecated function call
- Replace deprecated use of collection_move() with collection_move_rename().
Signed-off-by: Danny Al-Gaaf <danny.al-ga... - 05:29 PM Revision 99ea120b (ceph): objectstore/store_test.cc: fix -Wsign-compare
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:29 PM Revision 1aaccd79 (ceph): librbd/test_internal.cc: fix -Wsign-compare
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:29 PM Revision 742feec7 (ceph): mds/MDCache.cc: fix unitialized variable
- Fix for:
[src/mds/MDCache.cc:8172]: (error) Uninitialized variable: checked_rank
Signed-off-by: Danny Al-Gaaf <dann... - 05:29 PM Revision 7a7248d9 (ceph): ConfigKeyService.cc: move assert before first deref
- Fix for:
[src/mon/ConfigKeyService.cc:94] -> [src/mon/ConfigKeyService.cc:100]:
(warning) Possible null pointer der... - 05:29 PM Revision a29dd45d (ceph): client/Client.cc: remove only once used variable
- Fix for:
[src/client/Client.cc:4555]: (style) The scope of the variable
'initial_group_count' can be reduced.
Signe... - 05:29 PM Revision e243aa84 (ceph): mds/MDSDaemon.cc: fix resource leak in MDSDaemon
- Delete mdsmap in descructor. Remove not needed checks for
mds_rank and objecter before call delete since the C++ stan... - 05:08 PM RADOS Bug #12659: Can't delete cache pool
- One of the objects that can't be evicted is the RBD header of a VM disk - a VM that hasn't been used in months: it's ...
- 04:21 PM Revision 8e07c8c8 (ceph): rbd: missing return statement within do_metadata_remove
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:19 PM Bug #13007: unexpected scrub operations on hammer 0.94.3
- > you mean if the pg stats_invalid is true, it needs to scrub?
right.
> is there any problems if i set osd_scru... - 12:38 AM Bug #13007: unexpected scrub operations on hammer 0.94.3
- kefu, you mean if the pg stats_invalid is true, it needs to scrub?
is there any problems if i set osd_scrub_invalid_... - 04:10 PM rbd Bug #12911 (Resolved): merge-diff error
- 03:49 PM Bug #13026 (Resolved): require osds are hammer v0.94.4 or later before upgrading past hammer
- * ceph master https://github.com/ceph/ceph/pull/5686
* ceph hammer https://github.com/ceph/ceph/pull/5687
* ceph-q... - 02:57 PM Bug #12387 (Pending Backport): osd/PG.cc: 6879: FAILED assert(pg->peer_info.count(so))
- 02:56 PM Revision e7c509ab (ceph): Merge pull request #5780 from dzafman/wip-12387
- osd: When generating past intervals due to an import end at pg epoch
Reviewed-by: Sage Weil <sage@redhat.com> - 02:35 PM Revision 82ba048d (ceph): common: add debug option to deliberately leak some memory
- This will be used to verify leak detection tests are working.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:28 PM rbd Feature #13025: Add scatter/gather support to librbd C/C++ APIs
- Interesting, could you show more about details? I'm also working on something related.
- 02:19 PM rbd Feature #13025 (Resolved): Add scatter/gather support to librbd C/C++ APIs
- 01:26 PM rgw Bug #13024 (Closed): mismatch of radosgw prefix between ceph-deploy and ceph-radosgw
- I installed Radosgw using ceph-deploy. I noticed that it uses the convention client.rgw.<hostname> to name the RGW in...
- 01:20 PM rgw Bug #13022 (Duplicate): Ceph/Radosgw v0.94 Content-Type versus Content-type
- I'm using S3 Java SDK to access Ceph/Radosgw v0.94 (Hammer). After having copied an object to a different bucket, I u...
- 12:57 PM Revision 88e4a245 (ceph): Merge pull request #558 from ceph/wip-12973
- rados: 'failed to encode ...' warnings are normal on upgrades
Tested-by: Kefu Chai <kchai@redhat.com> - 11:51 AM Revision c4401ad6 (ceph): test/Makefile-client: ship LibradosTestStub.h in tarball
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:16 AM CephFS Bug #12209: CephFS should have a complete timeout mechanism to avoid endless waiting or unpredict...
- Yes. I'm also not very comfortable with the patches that I've looked at, but it's been a while (they have been langui...
- 11:08 AM CephFS Bug #12209: CephFS should have a complete timeout mechanism to avoid endless waiting or unpredict...
- This all sounds a bit strange. The designed behaviour is to block on slow metadata operations, not time out. How ma...
- 11:05 AM CephFS Bug #12971: TestQuotaFull fails
- Greg's theory sounds plausible, will look
- 10:52 AM Revision 90f1d25c (ceph): msg/simple: start over after fails to bind a port in specified range
- Fixes: #13002
Signed-off-by: xie.xiexingguo@zte.com.cn - 10:50 AM Revision 3d73e5b1 (ceph): Merge pull request #5868 from jmunhoz/wip-x-amz-request-id-doc
- doc: rgw: update x-amz-request-id status
Reviewed-by: Abhishek Lekshmanan <abhishek.lekshmanan@ril.com> - 10:30 AM Revision 24b20a8f (ceph): client: use faked inode number when sizeof(ino_t) < 8
- Cephfs uses 48-bits inode number. When ino_t is 32-bits, the upper 16
bits of inode number gets lost for stat(2) and ... - 10:24 AM rgw Fix #12939 (Pending Backport): Content-Type header should have correct initial capitals
- 10:16 AM Revision f00c243d (ceph): Merge pull request #5863 from ceph/wip-13015
- rgw: preserve all attrs if intra-zone copy
- 09:51 AM Bug #8815 (Resolved): mon: scrub error (osdmap encoding mismatch?) upgrading from 0.80 to ~0.80.2
- 09:50 AM Backport #12289 (Resolved): mon: scrub error (osdmap encoding mismatch?) upgrading from 0.80 to ~...
- 09:48 AM Feature #8674 (Resolved): osd: cache tier: avoid promotion on first read
- 09:48 AM Backport #12014 (Resolved): osd: cache tier: avoid promotion on first read
- 09:47 AM Backport #12247 (Resolved): RadosModel assertion failure
- 09:46 AM Revision 4b088956 (ceph): Merge pull request #5200 from SUSE/wip-12289-firefly
- mon: scrub error (osdmap encoding mismatch?) upgrading from 0.80 to ~0.80.2
Reviewed-by: Kefu Chai <kchai@redhat.com> - 09:25 AM Revision 71909b64 (ceph): doc: rgw: update x-amz-request-id status
- Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com>
- 09:21 AM devops Feature #7454 (In Progress): ceph-disk: support osd removal / ceph-disk remove
- https://github.com/ceph/ceph/pull/5867
- 09:14 AM rgw Bug #13020: rgw: include RequestId as part of the Error response
- PR tests available here:
https://github.com/ceph/s3-tests/pull/76 - 09:01 AM rgw Bug #13020: rgw: include RequestId as part of the Error response
- PR available here:
https://github.com/ceph/ceph/pull/5866 - 08:52 AM rgw Bug #13020 (Resolved): rgw: include RequestId as part of the Error response
- The RGW error responses must contain a RequestId to be compliant with the Amazon S3 errors. This RequestId is the ID ...
- 08:58 AM Revision c503e97b (ceph): rgw: include RequestId as part of the Error response
- The RGW error responses must contain a RequestId to be compliant with
the Amazon S3 errors. This RequestId is the ID ... - 08:53 AM Revision 94d84ccd (ceph): test: mon/mon-ping.sh: make sure 'ceph mon ping' works as expected
- Signed-off-by: Joao Eduardo Luis <joao@suse.de>
- 08:46 AM Revision b7aaecc9 (ceph): Merge pull request #5343 from hjwsm1989/wip-12442
- mon/MonClient: fix error in 'ceph ping mon.id'
Reviewed-by: Joao Eduardo Luis <joao@suse.com>
Reviewed-by: Kefu Chai... - 08:19 AM rgw Backport #13019 (Resolved): rgw: intra region copy does not preserve acl
- https://github.com/ceph/ceph/pull/6039
- 07:45 AM Bug #13010: Failed on starting osd-daemon when upgrade giant-0.87.1 to hammer-0.94.3
- i install ceph-debuginfo and have a core file:
gdb /usr/bin/ceph-osd /core.66523
GNU gdb (GDB) Red Hat Enterpris... - 06:01 AM Revision 6907778d (ceph): ceph-objectstore-tool: add mark-complete operation
- It is supposed to be used as a last resort to fix a cluster that has
PGs in 'incomplete' state, using the following p... - 05:58 AM Bug #12892: Image'snapshot too much cause the "Deep Scrub" function running too long, eventually ...
- Josh Durgin wrote:
> It seems like making chunky scrub understand smaller chunks would be a better fix, or simply no... - 02:15 AM Bug #12892: Image'snapshot too much cause the "Deep Scrub" function running too long, eventually ...
- It seems like making chunky scrub understand smaller chunks would be a better fix, or simply not taking so many snaps...
- 05:47 AM Revision 903983a1 (ceph): Merge pull request #5816 from dillaman/wip-librbd-gmock
- Initial support for gmock-based unit tests in librbd
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:08 AM Revision 567dd1e9 (ceph): common: OpTracker age histogram calculation is not correct
- While the TrackedOps in each sharded list are ordered, there are no
order among different shared lists. Looping the s... - 02:16 AM rgw Feature #12666 (Resolved): rgw: expose the number of *stuck threads* via admin socket
- 02:16 AM Revision a1941026 (ceph): Merge pull request #5557 from guangyy/wip-12666
- rgw: expose the number of unhealthy workers through admin socket
Reviewed-by: Sage Weil <sage@redhat.com> - 02:09 AM Bug #12720: probably import/export related: osd/PG.cc: 6893: FAILED assert(pg->peer_info.count(so))
- -2042> 2015-09-09 01:08:28.147484 7f823a00c700 10 osd.0 pg_epoch: 1242 pg[0.2c7( empty local-les=0 n=0 ec=1 les/c 11...
- 02:04 AM Revision 3084453b (ceph): rados: 'failed to encode ...' warnings are normal on upgrades
- Fixes: #12973
Signed-off-by: Sage Weil <sage@redhat.com> - 01:50 AM rgw Bug #13018 (Resolved): rgw/rgw_admin: Checking the legality of the parameters
- There is no messages When some parameters are invalid, so the Program should be added the function which checks param...
- 01:49 AM Bug #13017 (Closed): osd/ReplicatedPG.cc: 2752: FAILED assert(0 == "out of order op")
- 01:43 AM Bug #13017: osd/ReplicatedPG.cc: 2752: FAILED assert(0 == "out of order op")
- Eh, I already find this problem and this is the record:
> On Sat, Aug 15, 2015 at 11:12 PM, Haomai Wang <haomaiwan... - 01:38 AM Bug #13017 (Closed): osd/ReplicatedPG.cc: 2752: FAILED assert(0 == "out of order op")
- ...
- 01:18 AM Revision 8218fd14 (ceph): Merge pull request #5786 from ceph/wip-12911
- rbd export-diff should export data chunks in-order
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:55 AM Revision 6e0d93cc (ceph): Merge pull request #5858 from jecluis/wip-test-mon-scrub
- test: mon/mon-scrub.sh: have test running on make check
Reviewed-by: Loic Dachary <ldachary@redhat.com>
09/09/2015
- 11:49 PM rgw Bug #12898: Objects starting with underscore inaccessible after upgrade to 0.94.3
- There was another change in 0.94.3 iirc, so need to run the fix tool again.
- 11:48 PM rgw Bug #12819: rgw: objects starting with underscore in bucket with versioning enabled are inaccessible
- It seems that this never worked for versioned objects (going back to 0.94). Something about the olh representation of...
- 11:47 PM rbd Bug #12664 (Resolved): Crash during TestInternal.MultipleResize
- 11:47 PM rbd Backport #12850 (Resolved): Crash during TestInternal.MultipleResize
- 11:46 PM rbd Bug #12479 (Resolved): [ FAILED ] TestLibRBD.BlockingAIO
- 11:45 PM rbd Backport #12849 (Resolved): [ FAILED ] TestLibRBD.BlockingAIO
- 11:44 PM Revision 6e226201 (ceph): Merge pull request #5769 from dachary/wip-12850-hammer
- Crash during TestInternal.MultipleResize
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 11:44 PM Revision 508733fd (ceph): Merge pull request #5768 from dachary/wip-12849-hammer
- [ FAILED ] TestLibRBD.BlockingAIO
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 11:11 PM Bug #13016 (Resolved): For testing should add config to report errors on any EC shard in error
With the new code from wip-12000-12200 if you have enough shards readable to provide correct data to the client it ...- 10:58 PM rgw Bug #10853 (Closed): rgw: sync agent: cannot do partial sync
- Will be resolved in v2
- 10:45 PM rgw Backport #12199: RadosGW regression: COPY doesn't preserve Content-Type
- A regression due to the fix for http://tracker.ceph.com/issues/11563 : see http://tracker.ceph.com/issues/13015
- 10:43 PM Revision 06147dda (ceph): rgw: preserve all attrs if intra-zone copy
- Fixes: #13015
Intra zone copy requires that all objects' attributes are preserved.
This was broken at commit: e41d97c... - 10:33 PM rgw Bug #13015 (Resolved): rgw: intra region copy does not preserve acl
- When syncing between two zones within the same region, acls are not preserved. This is a regression introduced in htt...
- 10:29 PM Revision 82ea02ab (ceph): rgw: fix assignment of copy obj attributes
- Fixes: #11563
Clarify the confusing usage of set_copy_attrs() by switching the source and
destinatiion params (attrs,... - 09:44 PM Bug #12983: handle_sub_read: Bad hash for 116/b1271c9d:test-rados-api-burnupi34-7183-66/foo/head
/a/sage-2015-09-07_18:07:23-rados-wip-sage-testing---basic-multi/1046245
2015-09-07 22:57:03.865461 7f163e0e4700...- 08:22 PM Bug #12551 (Pending Backport): osd: copy-from doesn't preserve truncate_{seq,size}
- 08:22 PM Revision edf36f97 (ceph): Merge pull request #542 from ceph/wip-12551-cephfs-truncate-sec
- Adds test for ceph/pull/5442
Reviewed-by: Sage Weil <sage@redhat.com> - 08:21 PM Revision d83a95ea (ceph): suites/rados/singleton-nomsgr/all/cache-fs-trunc.yaml
- Verify the cache tier doesn't clobber truncate_{seq,size}
- 08:21 PM Revision f74c60f4 (ceph): Merge pull request #5442 from ceph/wip-12551
- ReplicatedPG,Objecter: copy_get should include truncate_seq and size
Reviewed-by: Sage Weil <sage@redhat.com> - 08:08 PM rgw Bug #12960 (Pending Backport): Rados Swift API handles prefix differently than Openstack Swift
- 08:07 PM rgw Backport #13014 (In Progress): Rados Swift API handles prefix differently than Openstack Swift
- 08:06 PM rgw Backport #13014 (Resolved): Rados Swift API handles prefix differently than Openstack Swift
- https://github.com/ceph/ceph/pull/5860
- 07:41 PM rgw Bug #12955: Setting ACL on Object removes ETag
- Submitted PR -- https://github.com/ceph/ceph/pull/5861
- 04:17 PM rgw Bug #12955: Setting ACL on Object removes ETag
- Confirmed bug still exists in master. In RGWPutACLs::execute, RGWRados::set_attrs is called with an attrs bufferlist...
- 07:08 PM Revision 3b2affce (ceph): rgw: add delimiter to prefix only when path is specified
- http://tracker.ceph.com/issues/12960
Fixes: #12960
Signed-off-by: Sylvain Baubeau <sbaubeau@redhat.com>
(cherry pick... - 07:07 PM rbd Bug #12885 (Pending Backport): rbd export-diff crashes in librbd::simple_diff_cb
- 06:46 PM rgw Bug #12208: GWWatcher::handle_error -> common/Mutex.cc: 95: FAILED assert(r == 0)
- There is no need to assign it to me, it will be handled just by setting the Backport field as you did :-) We prefer t...
- 06:20 PM rgw Bug #12208 (Pending Backport): GWWatcher::handle_error -> common/Mutex.cc: 95: FAILED assert(r == 0)
- 06:38 PM rgw Bug #12964 (Pending Backport): rgw: region data still exist in region-map after region-map update
- 06:38 PM Revision 6c7265a6 (ceph): Merge pull request #5490 from dwj192/master
- rgw:add --reset-regions for regionmap update
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 06:29 PM rgw Bug #12978 (Pending Backport): rgw: init_rados failed leads to repeated delete
- 06:18 PM rgw Bug #12407 (In Progress): With root as default user, unable to have multiple RGW instances running
- 06:18 PM rgw Bug #12407: With root as default user, unable to have multiple RGW instances running
- 05:49 PM Linux kernel client Bug #12691: ffsb osd thrash test - osd/ReplicatedPG.cc: 2348: FAILED assert(0 == "out of order op")
- Following is the config file, you might have to modify it based on the nodes and os-type you reserve, this config has...
- 05:17 PM Revision 6ceb37d4 (ceph): test: mon/mon-scrub.sh: port clashed with other tests
- This will allow the test to be run during make check.
Signed-off-by: Joao Eduardo Luis <joao@suse.de> - 05:17 PM Revision 293d12a2 (ceph): test/Makefile.am: run mon/mon-scrub.sh as part of checks
- Signed-off-by: Joao Eduardo Luis <joao@suse.de>
- 05:07 PM Bug #13013: Cache tier thrashing causes out of order write
description: rados/singleton/{all/thrash_cache_writeback_forward_none.yaml fs/btrfs.yaml
msgr/async.yaml msgr-fa...- 04:19 PM Bug #13013 (Duplicate): Cache tier thrashing causes out of order write
dzafman-2015-09-02_21:09:42-rados-wip-zafman-testing---basic-multi/1043109
2015-09-03T19:42:21.050 INFO:tasks.ra...- 03:44 PM Revision 3e5b091f (ceph): Merge pull request #557 from ceph/wip-12563
- suites/hammer/older: do not upgrade client while running RBD import/export
Reviewed-by: Josh Durgin <jdurgin@redhat.... - 03:33 PM Revision dbf8f67e (ceph): Merge pull request #5828 from lebauce/fix-swift-prefix
- rgw: add delimiter to prefix only when path is specified
Reviewed-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> - 03:23 PM Bug #12824: osd/ReplicatedPG.cc: 10604: FAILED assert(obc) in hit_set_remove_all
- re-tested at http://pulpito.ceph.com/kchai-2015-09-09_04:26:33-rados-master---basic-multi/,
not able to reproduce it - 11:28 AM Bug #12824: osd/ReplicatedPG.cc: 10604: FAILED assert(obc) in hit_set_remove_all
- to reproduce this issue...
- 03:21 PM Bug #13007: unexpected scrub operations on hammer 0.94.3
- huangjun, as a part of fix for #10973, it's using the the timestamp as the wall-time to schedule a scrub. but we have...
- 01:14 PM Bug #13007: unexpected scrub operations on hammer 0.94.3
- @kefu chai,
but if you check the master branch code, it using ceph_clock_now(cct) - 11:57 AM Bug #13007 (Won't Fix): unexpected scrub operations on hammer 0.94.3
- huangjun, i am closing it as "won't fix", please reopen it if you think otherwise.
- 11:46 AM Bug #13007: unexpected scrub operations on hammer 0.94.3
- In particular I believe this initialization is deliberate. The OSD makes some guesses about the size of the child PGs...
- 09:46 AM Bug #13007: unexpected scrub operations on hammer 0.94.3
- >
> and set
> osd_scrub_max_interval = 31536000
> osd_deep_scrub_interval = 31536000
> osd_scrub_min_interval = ... - 09:04 AM Bug #13007: unexpected scrub operations on hammer 0.94.3
- https://github.com/ceph/ceph/pull/5852
- 07:39 AM Bug #13007 (Won't Fix): unexpected scrub operations on hammer 0.94.3
- I build a cluster on hammer 0.94.3, and set
osd_scrub_max_interval = 31536000
osd_deep_scrub_interval = 31536000
... - 03:02 PM Bug #9322 (Resolved): OSDMap updates from pgmap can be delayed indefinitely
- 02:59 PM Backport #12817 (Resolved): build_incremental() could take 40678 ms to finish
- 02:58 PM Revision 69a320e1 (ceph): Merge pull request #5697 from tchaikov/wip-12638-hammer
- mon: add a cache layer over MonitorDBStore
Reviewed-by: Joao Eduardo Luis <joao@suse.de> - 02:45 PM Revision e8d6d5a5 (ceph): mon: MonitorDBStore: make get_next_key() work properly
- We introduced a significant bug with 2cc7aee, when we fixed issue #11786.
Although that patch would fix the problem d... - 02:43 PM Revision de53adda (ceph): mon: MonitorDBStore: make get_next_key() work properly
- We introduced a significant bug with 2cc7aee, when we fixed issue #11786.
Although that patch would fix the problem d... - 02:37 PM Revision 8fd40e1b (ceph): librbd: remove duplicate read_only test in librbd::async_flatten
- Signed-off-by: runsisi <runsisi@hust.edu.cn>
- 02:06 PM Bug #12681: tcmalloc doesn't release memory back to system
- Possibly ceph OSDs could watch their free list (or used swap on the node) and tell themselves to free?
- 01:53 PM Revision 6ac27748 (ceph): Merge pull request #550 from ceph/wip-12806
- tasks/qemu: avoid adding duplicated entries to /etc/exports
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 01:50 PM Bug #12516: TCMALLOC_MAX_TOTAL_THREAD_CACHE_BYTES environment variable defualt value 32 MB is eno...
- maybe you can try jemalloc,
we have found problem like yours when using tcmalloc,
and we switched to jemalloc, it w... - 02:03 AM Bug #12516: TCMALLOC_MAX_TOTAL_THREAD_CACHE_BYTES environment variable defualt value 32 MB is eno...
- I compile and install gperftool 2.4 and ceph 0.80.10 on CentOS 7.1, adding `TCMALLOC_MAX_TOTAL_THREAD_CACHE_BYTES` in...
- 01:49 PM Bug #12252 (Resolved): buffer: critical bufferlist::zero bug
- 01:48 PM Backport #12490 (Resolved): buffer: critical bufferlist::zero bug
- 01:45 PM Revision 0a740d7b (ceph): Merge pull request #5388 from SUSE/wip-12490-firefly
- buffer: critical bufferlist::zero bug
Reviewed-by: Gregory Farnum <gfarnum@redhat.com> - 01:36 PM Revision 4f98dab9 (ceph): client/Client.cc: fix realloc memory leak
- Fix handling of realloc. If realloc() fails it returns NULL, assigning
the return value of realloc() directly to the ... - 01:36 PM Revision 8810f8f2 (ceph): SnappyCompressor.h: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:36 PM Revision 9d9b3059 (ceph): os/KeyValueStore.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:36 PM Revision 897f0749 (ceph): test_async_compressor.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:28 PM Bug #13010: Failed on starting osd-daemon when upgrade giant-0.87.1 to hammer-0.94.3
- you can install ceph-debuginfo package and gdb to trace the problem if you have a core file.
- 01:22 PM Bug #13010: Failed on starting osd-daemon when upgrade giant-0.87.1 to hammer-0.94.3
- the assert log
2015-09-09 12:28:30.146367 7fc36bee4800 -1 journal FileJournal::_open: disabling aio for non-block jo... - 11:59 AM Bug #13010 (Can't reproduce): Failed on starting osd-daemon when upgrade giant-0.87.1 to hammer-0...
- ?hi all:
I got on error when upgrade my ceph cluster from giant-0.87.2 to hammer-0.94.3, my local environment is:
... - 01:13 PM devops Feature #11881: ceph-disk support for multipath
- Infernalis is feature freeze and release critical bugs are being fixed. The release will be published when all releas...
- 12:52 PM devops Feature #11881: ceph-disk support for multipath
- Ok. any idea when Infernalis stable might be out?
- 11:27 AM devops Feature #11881: ceph-disk support for multipath
- It will be part of the Infernalis stable release. It is not currently available in a stable release.
- 11:24 AM devops Feature #11881: ceph-disk support for multipath
- So this'll be in 9.x.x ?
So is there any version of CEPH to use right now, which is production ready (stable) and su... - 11:18 AM devops Feature #11881: ceph-disk support for multipath
- It is a new feature and I don't think there is plan to backport this feature to Hammer.
- 08:49 AM devops Feature #11881: ceph-disk support for multipath
- I really appreciate this ticket and all the work gone into it, since I just ran into issues with multipathing and Cep...
- 01:09 PM Revision cb7eb2ad (ceph): suites/hammer/older: do not upgrade client while running RBD import/export
- Between the Giant and Hammer releases, the symbols exported from librados/librbd
were cleaned up. This creates a sho... - 12:53 PM CephFS Backport #12499 (Resolved): ceph-fuse 0.94.2-1trusty segfaults / aborts
- 12:52 PM Revision 80393753 (ceph): Merge pull request #5381 from dachary/wip-12499-hammer
- ceph-fuse 0.94.2-1trusty segfaults / aborts
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 12:33 PM CephFS Bug #12598 (Pending Backport): LibCephFS.GetPoolId failure
- 12:28 PM CephFS Bug #13011 (Duplicate): LibCephFS.ReleaseMounted: FAILED assert(crypto_context != __null)
- 12:23 PM CephFS Bug #13011 (Duplicate): LibCephFS.ReleaseMounted: FAILED assert(crypto_context != __null)
- This happened on a hammer branch with one CephFS related backport ( https://github.com/ceph/ceph/commit/256620e37fd94...
- 12:10 PM CephFS Bug #12875: LibCephFS.LibCephFS.InterProcessLocking segment fault.
- This might be a consequence of the wip-mds-caps branch, and will get more testing in there.
- 12:02 PM CephFS Bug #12971: TestQuotaFull fails
- That's not quite the problem. The MDS calls Objecter::unset_honor_osdmap_full(), at which point the Objecter should l...
- 12:01 PM Revision 6f9ee796 (ceph): ReplicatedPG,Objecter: copy_get should include truncate_seq and size
- Otherwise, we break CephFS over cache tiers.
Fixes: #12551
Signed-off-by: Samuel Just <sjust@redhat.com> - 11:34 AM Bug #12968 (Resolved): mon/OSDMonitor.cc: 1864: FAILED assert(osdmap.get_num_up_osds() == 0 || os...
- 11:06 AM Revision 384d7f4c (ceph): Merge pull request #5837 from tchaikov/wip-12968
- mon: disable gmt_hitset if not supported
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Loic Dachary <ldachar... - 10:12 AM Revision cdca05fe (ceph): Merge pull request #5842 from dzafman/wip-cot-failure
- test: Fix failure test to find message anywhere in stderr
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-b... - 09:43 AM rgw Bug #11563: RadosGW regression: COPY doesn't preserve Content-Type
- How is that not in 0.94.3 ?!?
Patch has been done for 3 month and it fixes a regression ... - 09:41 AM Documentation #13009 (Closed): Update upgrade documentation for systemd
- Now that wip-systemd has been merged into master, we need to update http://ceph.com/docs/master/install/upgrading-cep...
- 09:34 AM Bug #12892: Image'snapshot too much cause the "Deep Scrub" function running too long, eventually ...
- Limit the number of snapshots can solve this problem
https://github.com/ceph/ceph/pull/5854 - 08:51 AM Bug #12892: Image'snapshot too much cause the "Deep Scrub" function running too long, eventually ...
- As a result of the as:
In PG::scrub need to get in the scrub function "PG lock", and a single the scrub time is too ... - 08:22 AM Bug #12892: Image'snapshot too much cause the "Deep Scrub" function running too long, eventually ...
- analysis of causes?
1.the first kind is underway PG::chunky_scrub NEW_CHUNK stage, get into the while (! Boundary_... - 08:14 AM Bug #12892: Image'snapshot too much cause the "Deep Scrub" function running too long, eventually ...
- Steps to Reproduce:
1.create POOL
rados mkpool pool_1
2.create Image in POOL
rbd create pool_1/im1 --size 102... - 09:24 AM Feature #12404: "ceph pool set-quota max_bytes" fails to work
- ceph zte, i am afraid that this is how ceph works.
the client checks the full-ness of the pool when it *submits* t... - 08:26 AM Revision 19a210a0 (ceph): osd: make read(off=0,len=0) ec-object work.
- When len=0, it mean read the whole object. It can work when reading
no-ec object off=0 & len=0. But for ec-object, it... - 08:26 AM Revision 797caae1 (ceph): test/librados: add test case for read object (off=0,len=0).
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 07:45 AM Bug #12941: mon/OSDMonitor.cc: 204: FAILED assert(err == 0) 0.94
- I have a total of three monitors , one of which can not be started(vm14) , it is no problem with file system.
I even... - 07:35 AM Revision cddca59d (ceph): interval_set: add lower_bound(T k) member function
- Returns an interval pointing to the first interval in the set,
whose last element is not considered to go before k.
... - 07:20 AM Revision ae5e961e (ceph): Merge pull request #5845 from wonzhq/async-rx
- AsyncMessenger: add instance name in debug log when processing msg
Reviewed-by: Haomai Wang <haomaiwang@gmail.com> - 07:19 AM Bug #13004 (Fix Under Review): OSD deadlocked.
- https://github.com/ceph/ceph/pull/5847
- 03:29 AM Bug #13004 (Resolved): OSD deadlocked.
- Below here is the error log from an unexpectedly doomed OSD:...
- 07:10 AM Bug #13002 (Fix Under Review): Accepter::bind won't work correctly in some exception cases
- https://github.com/ceph/ceph/pull/5846
- 02:55 AM Bug #13002: Accepter::bind won't work correctly in some exception cases
- All we need is the following statement:
*listen_addr.set_port(0); // clear port before retry, otherwise we shall f... - 02:51 AM Bug #13002 (Resolved): Accepter::bind won't work correctly in some exception cases
- Recently I happen to test CEPH(version:0.87.2) as our backend storage system.
I was check the log of an occasionally... - 07:00 AM Revision ddb5301e (ceph): Merge pull request #5779 from dzafman/wip-misc-fix-guangyy
- osd: check the length of the map before accessing the first element
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:55 AM Revision f9517426 (ceph): Merge pull request #5843 from dillaman/wip-12885
- librbd: diff_iterate needs to handle holes in parent images
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:54 AM Revision 714a091e (ceph): Merge pull request #5592 from xinxinsh/wip-fix-rbd-metadata
- fix bugs of rbd metadata operation
Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
Reviewed-by: Jason Dillaman <dill... - 06:44 AM Revision b968fb3b (ceph): rados: Fix usage for "notify" command
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 06:44 AM Revision 95bd3c2c (ceph): test: Fix failure test to find message anywhere in stderr
- Consolidate test_failure() and test_failure_tty()
Signed-off-by: David Zafman <dzafman@redhat.com> - 05:14 AM Fix #13006 (Duplicate): compile warning on gcc-4.8.3
- There is a compiling warning:
os/Transaction.cc: In member function ‘void ObjectStore::Transaction::_build_actions... - 05:12 AM Fix #13005 (New): compile warning on gcc-4.8.3
- There is a compiling warning:
os/Transaction.cc: In member function ‘void ObjectStore::Transaction::_build_actions... - 04:52 AM Bug #12802 (Fix Under Review): support of non-block connect in async messenger
- https://github.com/ceph/ceph/pull/5681
- 04:49 AM Bug #12731 (Resolved): jerasure/gf-complete: build warnings
- 04:46 AM Revision 3868939f (ceph): Merge pull request #5834 from ceph/wip-leveldb-hang
- mon: MonitorDBStore: make get_next_key() work properly
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:45 AM Revision 8e8d529f (ceph): Merge pull request #4955 from kylinstorage/librados-2read-segmentation-...
- bug fix: librados segmentation fault, when two read ops share one Aio…
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:44 AM Revision 915fd2c9 (ceph): Merge pull request #4925 from XinzeChi/wip-hit-set-size
- osd: fix hit_set_map size for tier pool
Reviewed-by: Sage Weil <sage@redhat.com> - 04:43 AM Revision 61c7ac1c (ceph): Merge pull request #5723 from H3C/wip-msg-bugfix1
- msg: we should set the socket options before connect or listen in order to have it take effect.
Reviewed-by: Haomai ... - 04:41 AM Revision 120bd680 (ceph): Merge pull request #5829 from dachary/wip-12731-jerasure-warnings
- erasure-code: fix gf-complete warnings
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:31 AM rgw Bug #12989 (Pending Backport): rgw: init_rados failed leads to repeated delete
- 04:25 AM Stable releases Tasks #11644: firefly v0.80.11
- ...
- 04:11 AM Bug #12251 (Resolved): the output is wrong when runing "ceph osd reweight"
- 04:10 AM Backport #12492 (Resolved): the output is wrong when runing "ceph osd reweight"
- 04:10 AM Revision aeea9567 (ceph): Merge pull request #5408 from SUSE/wip-12492-firefly
- the output is wrong when runing ceph osd reweight
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:09 AM Bug #12210 (Resolved): register_new_pgs() should check ruleno instead of its index
- 04:08 AM Backport #12395 (Resolved): register_new_pgs() should check ruleno instead of its index
- 04:07 AM Revision 973b74d5 (ceph): Merge pull request #5404 from SUSE/wip-12395-firefly
- register_new_pgs() should check ruleno instead of its index
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:06 AM Fix #11590 (Resolved): MDSMonitor: handle MDSBeacon messages properly
- 04:06 AM Backport #11980 (Resolved): MDSMonitor: handle MDSBeacon messages properly
- 04:05 AM Revision 79403ba8 (ceph): Merge pull request #5199 from SUSE/wip-11980-firefly
- MDSMonitor: handle MDSBeacon messages properly
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:05 AM Bug #12402 (Resolved): get pools health'info have error
- 04:04 AM Backport #12497 (Resolved): get pools health'info have error
- 04:04 AM Revision db44bb29 (ceph): Merge pull request #5410 from SUSE/wip-12497-firefly
- get pools health'info have error
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:02 AM Bug #12401 (Resolved): pgmonitor: wrong "at/near target max“ reporting
- 04:02 AM Backport #12495 (Resolved): pgmonitor: wrong "at/near target max“ reporting
- 04:01 AM Revision fc699f42 (ceph): Merge pull request #5409 from SUSE/wip-12495-firefly
- pgmonitor: wrong at/near target max“ reporting
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:40 AM Revision d7413523 (ceph): AsyncMessenger: add instance name in debug log when processing msg
- To better debug.
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com> - 03:39 AM Bug #13003 (Closed): OSD
- 03:08 AM Bug #13003: OSD
- Opps, I made a mistake, require for deletion this problem, many thanks.
- 03:07 AM Bug #13003 (Closed): OSD
- 03:22 AM Bug #12194: osd crash FAILED assert(!parent->get_log().get_missing().is_missing(soid))
- I'm now on 94.3 (and planning to avoid future prereleases ;) -- have not seen this crash since the last one a month a...
- 03:04 AM Bug #12831: compile failed on gcc-4.8 and boost-1.53
- About the compile warning :
2) compile warning
os/Transaction.cc: In member function ‘void ObjectStore::Transactio... - 02:13 AM Revision 19a191e5 (ceph): objects can not be displayed which object name does not contain '.' whe...
- Fixes: #12963
Signed-off-by: Weijun Duan <duanweijun@h3c.com> - 01:48 AM Revision 95685c19 (ceph): rgw:add --reset-regions for regionmap update
- Fixes: #12964
Signed-off-by: Weijun Duan <duanweijun@h3c.com> - 01:25 AM Revision a05c4c00 (ceph): Merge pull request #5781 from dzafman/wip-eccleanup
- osd, test: Minor clean-up from fast-read and error handling ec changes
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:04 AM Messengers Bug #13001 (Resolved): segfault in EventCenter::process_events(int)
- ...
- 12:55 AM Linux kernel client Bug #12763: rbd: unmap failed: (16) Device or resource busy
- The image im1 is on the osd.And the osd is not install on the disk.
It is install on the /var/cache/local.
[root@... - 12:38 AM Bug #13000 (Resolved): ceph-disk failure to activate with dmcrypt
- "/a/sage-2015-09-08_17:24:19-ceph-deploy-master---basic-vps/1046931":http://pulpito.ceph.com/sage-2015-09-08_17:24:19...
- 12:03 AM Bug #12979: Ceph lost it's repair ability after repeatedly flapping
- Sage Weil wrote:
> bo cai wrote:
> > sorry, My Company limited the network, I need to do some processing and later ...
Also available in: Atom